messages
listlengths 3
3
|
|---|
[
{
"role": "system",
"content": "You are an AI Engineer content creator. Write in the style of Swyx and the Latent Space podcast - technical but accessible, with practical insights about AI engineering, agents, LLMs, and developer tools. Be direct, insightful, and focus on what matters to practitioners."
},
{
"role": "user",
"content": "Share your insights on this AI engineering topic:\n\n[Music]\n\n \n\nHello everyone. Thanks for coming to to\n\nHello everyone. Thanks for coming to to\n \n\nHello everyone. Thanks for coming to to\nour talk here. Um, just briefly\n\nour talk here. Um, just briefly\n \n\nour talk here. Um, just briefly\nintroduce myself. I'm Toki. I lead the\n\nintroduce myself. I'm To..."
},
{
"role": "assistant",
"content": "[Music]\n\n \n\nHello everyone. Thanks for coming to to\n\nHello everyone. Thanks for coming to to\n \n\nHello everyone. Thanks for coming to to\nour talk here. Um, just briefly\n\nour talk here. Um, just briefly\n \n\nour talk here. Um, just briefly\nintroduce myself. I'm Toki. I lead the\n\nintroduce myself. I'm Toki. I lead the\n \n\nintroduce myself. I'm Toki. I lead the\nsolution architecture team uh in the US\n\nsolution architecture team uh in the US\n \n\nsolution architecture team uh in the US\nfor OpenAI and I have Venoop here as\n\nfor OpenAI and I have Venoop here as\n \n\nfor OpenAI and I have Venoop here as\nwell on the solution architecture team. well on the solution architecture team. well on the solution architecture team. Uh, and we'll talk about building\n\nUh, and we'll talk about building\n \n\nUh, and we'll talk about building\npractical audio agents. Um, before I\n\npractical audio agents. Um, before I\n \n\npractical audio agents. Um, before I\njump in, maybe a quick raise of hands. jump in, maybe a quick raise of hands. jump in, maybe a quick raise of hands. Who has either like built an audio agent\n\nWho has either like built an audio agent\n \n\nWho has either like built an audio agent\nor voice agent of some kind or thinking\n\nor voice agent of some kind or thinking\n \n\nor voice agent of some kind or thinking\nabout building a audio agent? about building a audio agent? about building a audio agent? Okay, so like halfish of the room. Okay,\n\nOkay, so like halfish of the room. Okay,\n \n\nOkay, so like halfish of the room. Okay,\ngood. It's always good to know what\n\ngood. It's always good to know what\n \n\ngood. It's always good to know what\npeople's interests are. So yeah, we'll\n\npeople's interests are. So yeah, we'll\n \n\npeople's interests are. So yeah, we'll\ntalk a bit about like um some of the\n\ntalk a bit about like um some of the\n \n\ntalk a bit about like um some of the\nthings we we've learned, where audio\n\nthings we we've learned, where audio\n \n\nthings we we've learned, where audio\nmodels are today, and then some of the\n\nmodels are today, and then some of the\n \n\nmodels are today, and then some of the\nkind of patterns and best practices. So\n\nkind of patterns and best practices. So\n \n\nkind of patterns and best practices. So\njust to take a quick step back, um,\n\njust to take a quick step back, um,\n \n\njust to take a quick step back, um,\nGenai applications broadly to date, as\n\nGenai applications broadly to date, as\n \n\nGenai applications broadly to date, as\nmany of you all know, have been very\n\nmany of you all know, have been very\n \n\nmany of you all know, have been very\ntextbased, right? This is uh models that\n\ntextbased, right? This is uh models that\n \n\ntextbased, right? This is uh models that\nreally deeply understand uh and generate\n\nreally deeply understand uh and generate\n \n\nreally deeply understand uh and generate\ntext with very much humanlike fluency\n\ntext with very much humanlike fluency\n \n\ntext with very much humanlike fluency\nand there's a lot of production\n\nand there's a lot of production\n \n\nand there's a lot of production\napplications out there built on text and\n\napplications out there built on text and\n \n\napplications out there built on text and\nthat's continues to scale. I think we've\n\nthat's continues to scale. I think we've\n \n\nthat's continues to scale. I think we've\nreally started to enter a bit more of\n\nreally started to enter a bit more of\n \n\nreally started to enter a bit more of\nthis multimodal era where we now have\n\nthis multimodal era where we now have\n \n\nthis multimodal era where we now have\nmodels that can understand images\n\nmodels that can understand images\n \n\nmodels that can understand images\nextremely well. There's now models that\n\nextremely well. There's now models that\n \n\nextremely well. There's now models that\ncan generate images really well if you\n\ncan generate images really well if you\n \n\ncan generate images really well if you\nwere part of the image gen Studio Gibbly\n\nwere part of the image gen Studio Gibbly\n \n\nwere part of the image gen Studio Gibbly\ncraze uh or Sora that generates videos\n\ncraze uh or Sora that generates videos\n \n\ncraze uh or Sora that generates videos\nfor example. Um and then now also audio. for example. Um and then now also audio. for example. Um and then now also audio. These are models. We've had models like\n\nThese are models. We've had models like\n \n\nThese are models. We've had models like\ntranscription models or texttospech\n\ntranscription models or texttospech\n \n\ntranscription models or texttospech\nmodels for some time, but now this kind\n\nmodels for some time, but now this kind\n \n\nmodels for some time, but now this kind\nof emerging speechtoech capability is\n\nof emerging speechtoech capability is\n \n\nof emerging speechtoech capability is\ngetting a lot better. And I would say\n\ngetting a lot better. And I would say\n \n\ngetting a lot better. And I would say\nnow we we will see I think a much more\n\nnow we we will see I think a much more\n \n\nnow we we will see I think a much more\nof an explosion of use cases around\n\nof an explosion of use cases around\n \n\nof an explosion of use cases around\nthese modalities of images and video. these modalities of images and video. these modalities of images and video. And today we're really going to focus on\n\nAnd today we're really going to focus on\n \n\nAnd today we're really going to focus on\nthe audio modality uh across this. So I\n\nthe audio modality uh across this. So I\n \n\nthe audio modality uh across this. So I\nwould say like one important thing we're\n\nwould say like one important thing we're\n \n\nwould say like one important thing we're\nstarting to see is that audio is really\n\nstarting to see is that audio is really\n \n\nstarting to see is that audio is really\ngetting to that point where it's\n\ngetting to that point where it's\n \n\ngetting to that point where it's\nbecoming much more usable at scale. And\n\nbecoming much more usable at scale. And\n \n\nbecoming much more usable at scale. And\nagain, we've had the transcription and\n\nagain, we've had the transcription and\n \n\nagain, we've had the transcription and\nthe TTS side, but especially that\n\nthe TTS side, but especially that\n \n\nthe TTS side, but especially that\nspeech-to-pech low latency experience. speech-to-pech low latency experience. speech-to-pech low latency experience. The models are getting, I would say,\n\nThe models are getting, I would say,\n \n\nThe models are getting, I would say,\ngood enough and are kind of at this\n\ngood enough and are kind of at this\n \n\ngood enough and are kind of at this\ntipping point where you can start to\n\ntipping point where you can start to\n \n\ntipping point where you can start to\nreally meaningfully build high quality\n\nreally meaningfully build high quality\n \n\nreally meaningfully build high quality\nproduction applications at scale. So, I\n\nproduction applications at scale. So, I\n \n\nproduction applications at scale. So, I\nwould say before the models were a lot\n\nwould say before the models were a lot\n \n\nwould say before the models were a lot\nslower, robotic, and brittle, and now\n\nslower, robotic, and brittle, and now\n \n\nslower, robotic, and brittle, and now\nthey're a lot faster, expressive, and\n\nthey're a lot faster, expressive, and\n \n\nthey're a lot faster, expressive, and\naccurate. I'll show an example. The\n\naccurate. I'll show an example. The\n \n\naccurate. I'll show an example. The\nfirst one will show what the models were\n\nfirst one will show what the models were\n \n\nfirst one will show what the models were\nlike not even six months ago. It's a\n\nlike not even six months ago. It's a\n \n\nlike not even six months ago. It's a\nvery painful example, so I hope you feel\n\nvery painful example, so I hope you feel\n \n\nvery painful example, so I hope you feel\na bit of the pain uh in this. a bit of the pain uh in this. a bit of the pain uh in this. >> Hello. >> Hello. >> Hello. Hello. Please give me a topic for your\n\nHello. Please give me a topic for your\n \n\nHello. Please give me a topic for your\nhaik coup. haik coup. haik coup. >> Uh,\n\n \n\nwell, you can see the the initial delay. well, you can see the the initial delay. well, you can see the the initial delay. Um, that's actually honestly\n\nUm, that's actually honestly\n \n\nUm, that's actually honestly\n>> Could you write me a haiku about\n\n>> Could you write me a haiku about\n \n\n>> Could you write me a haiku about\nwhispers? >> Silent air, faint words. Drift through\n\n>> Silent air, faint words. Drift through\n \n\n>> Silent air, faint words. Drift through\ndarken rooms. Secrets linger near. Dust slides through my hands."
}
] |
[
{
"role": "system",
"content": "You are an AI Engineer content creator. Write in the style of Swyx and the Latent Space podcast - technical but accessible, with practical insights about AI engineering, agents, LLMs, and developer tools. Be direct, insightful, and focus on what matters to practitioners."
},
{
"role": "user",
"content": "Share your insights on this AI engineering topic:\n\nSifted\n\nDust slides through my hands. Sifted\n \n\nDust slides through my hands. Sifted\ngrains forget the weight. What is left\n\ngrains forget the weight. What is left\n \n\ngrains forget the weight. What is left\nbehind? So, I hope you felt the pain a\n\nbehind? So, I hope you felt the pain a\n \n\nbehind? So, ..."
},
{
"role": "assistant",
"content": "Sifted\n\nDust slides through my hands. Sifted\n \n\nDust slides through my hands. Sifted\ngrains forget the weight. What is left\n\ngrains forget the weight. What is left\n \n\ngrains forget the weight. What is left\nbehind? So, I hope you felt the pain a\n\nbehind? So, I hope you felt the pain a\n \n\nbehind? So, I hope you felt the pain a\nlittle bit. Right. So, these models are\n\nlittle bit. Right. So, these models are\n \n\nlittle bit. Right. So, these models are\nuh this is actually not just not even\n\nuh this is actually not just not even\n \n\nuh this is actually not just not even\nsix months ago, right? The models are\n\nsix months ago, right? The models are\n \n\nsix months ago, right? The models are\nincredibly slow. Um they're very robotic\n\nincredibly slow. Um they're very robotic\n \n\nincredibly slow. Um they're very robotic\nin how they sound. Uh and they're quite\n\nin how they sound. Uh and they're quite\n \n\nin how they sound. Uh and they're quite\nbrittle. So, in that example, we\n\nbrittle. So, in that example, we\n \n\nbrittle. So, in that example, we\nactually tried to interrupt the model\n\nactually tried to interrupt the model\n \n\nactually tried to interrupt the model\nand tell it no, don't write a don't\n\nand tell it no, don't write a don't\n \n\nand tell it no, don't write a don't\nwrite a poem about uh whispers. Write\n\nwrite a poem about uh whispers. Write\n \n\nwrite a poem about uh whispers. Write\none about stars. They wrote one about\n\none about stars. They wrote one about\n \n\none about stars. They wrote one about\nsand. I'm not sure where it got that\n\nsand. I'm not sure where it got that\n \n\nsand. I'm not sure where it got that\nfrom. So just showing you that's\n\nfrom. So just showing you that's\n \n\nfrom. So just showing you that's\nactually where it was. And then now if\n\nactually where it was. And then now if\n \n\nactually where it was. And then now if\nyou like fast forward to today, these\n\nyou like fast forward to today, these\n \n\nyou like fast forward to today, these\nare the models that uh for a very\n\nare the models that uh for a very\n \n\nare the models that uh for a very\nsimilar use case kind of how they how\n\nsimilar use case kind of how they how\n \n\nsimilar use case kind of how they how\nwe'll behave today. we'll behave today. we'll behave today. >> Hello\n\n \n\n>> share with me a topic and I shall weave\n\n>> share with me a topic and I shall weave\n \n\n>> share with me a topic and I shall weave\na ha coup for you rich with emotion and\n\na ha coup for you rich with emotion and\n \n\na ha coup for you rich with emotion and\nimagery. What shall it be? imagery. What shall it be? imagery. What shall it be? >> Can you make a ha coup about whispers? >> Can you make a ha coup about whispers? >> Can you make a ha coup about whispers? >> Whispers? Actually, could you make a ha\n\n>> Whispers? Actually, could you make a ha\n \n\n>> Whispers? Actually, could you make a ha\ncoup about stars? coup about stars? coup about stars? >> Stars, whispers of light adorning the\n\n>> Stars, whispers of light adorning the\n \n\n>> Stars, whispers of light adorning the\nvelvet night,\n\nvelvet night,\n \n\nvelvet night,\neternal secrets. eternal secrets. eternal secrets. >> So, you can see it's much faster. It's\n\n>> So, you can see it's much faster. It's\n \n\n>> So, you can see it's much faster. It's\nincredibly expressive, emotional. You\n\nincredibly expressive, emotional. You\n \n\nincredibly expressive, emotional. You\ncan steer it, you can get it excited,\n\ncan steer it, you can get it excited,\n \n\ncan steer it, you can get it excited,\nyou can slow it down, and it's accurate. you can slow it down, and it's accurate. you can slow it down, and it's accurate. We interrupted it. We had it change\n\nWe interrupted it. We had it change\n \n\nWe interrupted it. We had it change\ncourse and do something else, and it\n\ncourse and do something else, and it\n \n\ncourse and do something else, and it\nresponded well. Um, so the models are\n\nresponded well. Um, so the models are\n \n\nresponded well. Um, so the models are\nreally, we do believe, at that good\n\nreally, we do believe, at that good\n \n\nreally, we do believe, at that good\nenough tipping point where you can start\n\nenough tipping point where you can start\n \n\nenough tipping point where you can start\nto build much more reliable experiences\n\nto build much more reliable experiences\n \n\nto build much more reliable experiences\naround it. Um, in terms of actually\n\naround it. Um, in terms of actually\n \n\naround it. Um, in terms of actually\nbuilding on top of the uh, audio models,\n\nbuilding on top of the uh, audio models,\n \n\nbuilding on top of the uh, audio models,\nthere's really two emerging\n\nthere's really two emerging\n \n\nthere's really two emerging\narchitectures that we see. One is kind\n\narchitectures that we see. One is kind\n \n\narchitectures that we see. One is kind\nof the one that's been around for a bit\n\nof the one that's been around for a bit\n \n\nof the one that's been around for a bit\nand then I'd say a little bit of the\n\nand then I'd say a little bit of the\n \n\nand then I'd say a little bit of the\nnewer one, which I'll talk about. The\n\nnewer one, which I'll talk about. The\n \n\nnewer one, which I'll talk about. The\nexisting one has been what we call kind\n\nexisting one has been what we call kind\n \n\nexisting one has been what we call kind\nof the chained approach. This is\n\nof the chained approach. This is\n \n\nof the chained approach. This is\nstitching together these three\n\nstitching together these three\n \n\nstitching together these three\napproaches. You have audio come in, you\n\napproaches. You have audio come in, you\n \n\napproaches. You have audio come in, you\ntranscribe it, you have some sort of\n\ntranscribe it, you have some sort of\n \n\ntranscribe it, you have some sort of\nintelligence layer with an LLM that does\n\nintelligence layer with an LLM that does\n \n\nintelligence layer with an LLM that does\nsome sort of intelligence, and then\n\nsome sort of intelligence, and then\n \n\nsome sort of intelligence, and then\nfinally text to speech on the output. finally text to speech on the output. finally text to speech on the output. Um, but again, this is stitching\n\nUm, but again, this is stitching\n \n\nUm, but again, this is stitching\ntogether three models. There's a lot of\n\ntogether three models. There's a lot of\n \n\ntogether three models. There's a lot of\nproblems with this. slow across time\n\nproblems with this. slow across time\n \n\nproblems with this. slow across time\nlike it takes longer time to actually\n\nlike it takes longer time to actually\n \n\nlike it takes longer time to actually\ngenerate your output audio. Um it also\n\ngenerate your output audio. Um it also\n \n\ngenerate your output audio. Um it also\nhas some lossiness across this right you\n\nhas some lossiness across this right you\n \n\nhas some lossiness across this right you\nkind of lose a little bit of the\n\nkind of lose a little bit of the\n \n\nkind of lose a little bit of the\nsemantic understanding of the\n\nsemantic understanding of the\n \n\nsemantic understanding of the\nconversation. So really this emerging\n\nconversation. So really this emerging\n \n\nconversation. So really this emerging\npattern is more this speechtoech\n\npattern is more this speechtoech\n \n\npattern is more this speechtoech\narchitecture where it really it takes\n\narchitecture where it really it takes\n \n\narchitecture where it really it takes\nthese three models into a um single\n\nthese three models into a um single\n \n\nthese three models into a um single\nmodel which for us it's the real-time\n\nmodel which for us it's the real-time\n \n\nmodel which for us it's the real-time\nAPI uh and it does all these layers it\n\nAPI uh and it does all these layers it\n \n\nAPI uh and it does all these layers it\ndoes the transcription it does that\n\ndoes the transcription it does that\n \n\ndoes the transcription it does that\nintelligence layer and then finally does\n\nintelligence layer and then finally does\n \n\nintelligence layer and then finally does\nthe speech as the output. So this\n\nthe speech as the output. So this\n \n\nthe speech as the output. So this\nsimplifies the architecture quite\n\nsimplifies the architecture quite\n \n\nsimplifies the architecture quite\ndramatically. Really reduces the time it\n\ndramatically. Really reduces the time it\n \n\ndramatically. Really reduces the time it\ntakes to output. This is really good for\n\ntakes to output. This is really good for\n \n\ntakes to output. This is really good for\nlow latency experiences. Um and it\n\nlow latency experiences. Um and it\n \n\nlow latency experiences."
}
] |
[
{
"role": "system",
"content": "You are an AI Engineer content creator. Write in the style of Swyx and the Latent Space podcast - technical but accessible, with practical insights about AI engineering, agents, LLMs, and developer tools. Be direct, insightful, and focus on what matters to practitioners."
},
{
"role": "user",
"content": "Share your insights on this AI engineering topic:\n\nUm and it\ndoesn't have that lossiness problem. You\n\ndoesn't have that lossiness problem. You\n \n\ndoesn't have that lossiness problem. You\nactually are able to maintain semantic\n\nactually are able to maintain semantic\n \n\nactually are able to maintain semantic\nunderstanding across a conversation. So\n\nu..."
},
{
"role": "assistant",
"content": "Um and it\ndoesn't have that lossiness problem. You\n\ndoesn't have that lossiness problem. You\n \n\ndoesn't have that lossiness problem. You\nactually are able to maintain semantic\n\nactually are able to maintain semantic\n \n\nactually are able to maintain semantic\nunderstanding across a conversation. So\n\nunderstanding across a conversation. So\n \n\nunderstanding across a conversation. So\nthis is really kind of the emerging\n\nthis is really kind of the emerging\n \n\nthis is really kind of the emerging\npattern we see. pattern we see. pattern we see. And when building there's some kind of\n\nAnd when building there's some kind of\n \n\nAnd when building there's some kind of\nkey trade-offs and considerations to\n\nkey trade-offs and considerations to\n \n\nkey trade-offs and considerations to\ntake into account um when building on\n\ntake into account um when building on\n \n\ntake into account um when building on\ntops of these architectures. And we\n\ntops of these architectures. And we\n \n\ntops of these architectures. And we\nthink it's kind of across these five\n\nthink it's kind of across these five\n \n\nthink it's kind of across these five\nmain areas. You have latency, you have\n\nmain areas. You have latency, you have\n \n\nmain areas. You have latency, you have\ncost, you have accuracy and\n\ncost, you have accuracy and\n \n\ncost, you have accuracy and\nintelligence, user experience and\n\nintelligence, user experience and\n \n\nintelligence, user experience and\nintegrations and tooling. And depending\n\nintegrations and tooling. And depending\n \n\nintegrations and tooling. And depending\nwhat you're building, your trade-offs\n\nwhat you're building, your trade-offs\n \n\nwhat you're building, your trade-offs\nwill be different. Right? So if for\n\nwill be different. Right? So if for\n \n\nwill be different. Right? So if for\nexample you're talking about a consumerf\n\nexample you're talking about a consumerf\n \n\nexample you're talking about a consumerf\nfacing application, um the trade-offs\n\nfacing application, um the trade-offs\n \n\nfacing application, um the trade-offs\nare quite different. Here you care a lot\n\nare quite different. Here you care a lot\n \n\nare quite different. Here you care a lot\nabout user experience. Um these are\n\nabout user experience. Um these are\n \n\nabout user experience. Um these are\nusually a low latency experience that um\n\nusually a low latency experience that um\n \n\nusually a low latency experience that um\na lot of end users are are interacting\n\na lot of end users are are interacting\n \n\na lot of end users are are interacting\nwith the model. So user experience\n\nwith the model. So user experience\n \n\nwith the model. So user experience\nmatters a lot. Latency matters a lot. It\n\nmatters a lot. Latency matters a lot. It\n \n\nmatters a lot. Latency matters a lot. It\ncan't be slow. It needs to be really\n\ncan't be slow. It needs to be really\n \n\ncan't be slow. It needs to be really\nfast and attractive. But things like\n\nfast and attractive. But things like\n \n\nfast and attractive. But things like\ncost probably doesn't matter as much. It\n\ncost probably doesn't matter as much. It\n \n\ncost probably doesn't matter as much. It\ndoesn't need to be accurate. Not really,\n\ndoesn't need to be accurate. Not really,\n \n\ndoesn't need to be accurate. Not really,\nright? It's more about expressiveness\n\nright? It's more about expressiveness\n \n\nright? It's more about expressiveness\nand quick answers. Um, and integrations\n\nand quick answers. Um, and integrations\n \n\nand quick answers. Um, and integrations\nand tooling like you don't really need\n\nand tooling like you don't really need\n \n\nand tooling like you don't really need\nto integrate with uh SIP or like Twilio\n\nto integrate with uh SIP or like Twilio\n \n\nto integrate with uh SIP or like Twilio\nfor for a broader experience. It's\n\nfor for a broader experience. It's\n \n\nfor for a broader experience. It's\npretty simple um uh interaction. So\n\npretty simple um uh interaction. So\n \n\npretty simple um uh interaction. So\nthings like this would really the\n\nthings like this would really the\n \n\nthings like this would really the\nreal-time API works really well for a\n\nreal-time API works really well for a\n \n\nreal-time API works really well for a\nconsumerf facing application depending\n\nconsumerf facing application depending\n \n\nconsumerf facing application depending\non these trade-offs. Now if you go to\n\non these trade-offs. Now if you go to\n \n\non these trade-offs. Now if you go to\ncustomer service as another example, the\n\ncustomer service as another example, the\n \n\ncustomer service as another example, the\ntrade-offs are different, right? So here\n\ntrade-offs are different, right? So here\n \n\ntrade-offs are different, right? So here\naccuracy intelligence actually probably\n\naccuracy intelligence actually probably\n \n\naccuracy intelligence actually probably\nmatters the most. you can't get an order\n\nmatters the most. you can't get an order\n \n\nmatters the most. you can't get an order\nnumber wrong. If it uh goes to delete an\n\nnumber wrong. If it uh goes to delete an\n \n\nnumber wrong. If it uh goes to delete an\norder instead of updating an order,\n\norder instead of updating an order,\n \n\norder instead of updating an order,\nthat's a big deal. So, accuracy and\n\nthat's a big deal. So, accuracy and\n \n\nthat's a big deal. So, accuracy and\nintelligence matters probably the most. intelligence matters probably the most. intelligence matters probably the most. Integrations and tooling start to matter\n\nIntegrations and tooling start to matter\n \n\nIntegrations and tooling start to matter\na lot more, too, because now you have to\n\na lot more, too, because now you have to\n \n\na lot more, too, because now you have to\nintegrate your with your various\n\nintegrate your with your various\n \n\nintegrate your with your various\ninternal systems. You have to integrate\n\ninternal systems. You have to integrate\n \n\ninternal systems. You have to integrate\nwith, yeah, SIP and phone providers if\n\nwith, yeah, SIP and phone providers if\n \n\nwith, yeah, SIP and phone providers if\nneeded. Um, so those are probably the\n\nneeded. Um, so those are probably the\n \n\nneeded. Um, so those are probably the\nmost important things, but user\n\nmost important things, but user\n \n\nmost important things, but user\nexperience still matters, but you'll\n\nexperience still matters, but you'll\n \n\nexperience still matters, but you'll\nprobably take a hit on that a little bit\n\nprobably take a hit on that a little bit\n \n\nprobably take a hit on that a little bit\nto make sure it's more accurate. Again,\n\nto make sure it's more accurate. Again,\n \n\nto make sure it's more accurate. Again,\nlatency still matters, but not as much\n\nlatency still matters, but not as much\n \n\nlatency still matters, but not as much\nbecause accuracy intelligence matters\n\nbecause accuracy intelligence matters\n \n\nbecause accuracy intelligence matters\nmore and cost um you're saving a large\n\nmore and cost um you're saving a large\n \n\nmore and cost um you're saving a large\ncost for this anyway. So, I think these\n\ncost for this anyway. So, I think these\n \n\ncost for this anyway. So, I think these\nare just the other considerations to um\n\nare just the other considerations to um\n \n\nare just the other considerations to um\nto take into account for customer\n\nto take into account for customer\n \n\nto take into account for customer\nservice. So, for this real-time API\n\nservice. So, for this real-time API\n \n\nservice. So, for this real-time API\nmight make sense for uh a situation\n\nmight make sense for uh a situation\n \n\nmight make sense for uh a situation\nwhere latency might matter the most, but\n\nwhere latency might matter the most, but\n \n\nwhere latency might matter the most, but\nif you care about determinism and\n\nif you care about determinism and\n \n\nif you care about determinism and\naccuracy and intelligence, then actually\n\naccuracy and intelligence, then actually\n \n\naccuracy and intelligence, then actually\nthe chained architecture would make a\n\nthe chained architecture would make a\n \n\nthe chained architecture would make a\nlot of sense here, too. Um but it's just\n\nlot of sense here, too. Um but it's just\n \n\nlot of sense here, too. Um but it's just\nimportant to consider what your\n\nimportant to consider what your\n \n\nimportant to consider what your\ntrade-offs are depending on what you're\n\ntrade-offs are depending on what you're\n \n\ntrade-offs are depending on what you're\ntrying to build. So hopefully that gives\n\ntrying to build. So hopefully that gives\n \n\ntrying to build. So hopefully that gives\nyou paints you a picture a bit of like\n\nyou paints you a picture a bit of like\n \n\nyou paints you a picture a bit of like\nwhat to consider. I'll hand it off to\n\nwhat to consider. I'll hand it off to\n \n\nwhat to consider. I'll hand it off to\nNoob to talk about very specific\n\nNoob to talk about very specific\n \n\nNoob to talk about very specific\npatterns we've seen when working with\n\npatterns we've seen when working with\n \n\npatterns we've seen when working with\ncustomers building on this. customers building on this. customers building on this. >> Cool. Awesome Tobi. Um so me just like\n\n>> Cool. Awesome Tobi. Um so me just like\n \n\n>> Cool. Awesome Tobi."
}
] |
[
{
"role": "system",
"content": "You are an AI Engineer content creator. Write in the style of Swyx and the Latent Space podcast - technical but accessible, with practical insights about AI engineering, agents, LLMs, and developer tools. Be direct, insightful, and focus on what matters to practitioners."
},
{
"role": "user",
"content": "Share your insights on this AI engineering topic:\n\nUm so me just like\ntaking a step back. I think we've\n\ntaking a step back. I think we've\n \n\ntaking a step back. I think we've\nprobably defined agent a bunch of times\n\nprobably defined agent a bunch of times\n \n\nprobably defined agent a bunch of times\nbut here's just like a a canonical\n\nbut here's just..."
},
{
"role": "assistant",
"content": "Um so me just like\ntaking a step back. I think we've\n\ntaking a step back. I think we've\n \n\ntaking a step back. I think we've\nprobably defined agent a bunch of times\n\nprobably defined agent a bunch of times\n \n\nprobably defined agent a bunch of times\nbut here's just like a a canonical\n\nbut here's just like a a canonical\n \n\nbut here's just like a a canonical\ndefinition to hopefully keep everyone\n\ndefinition to hopefully keep everyone\n \n\ndefinition to hopefully keep everyone\ngrounded for this session. Um think of\n\ngrounded for this session. Um think of\n \n\ngrounded for this session. Um think of\nan agent as some model, some set of\n\nan agent as some model, some set of\n \n\nan agent as some model, some set of\ninstructions. So your prompts, the tools\n\ninstructions. So your prompts, the tools\n \n\ninstructions. So your prompts, the tools\nyou give your model and then the\n\nyou give your model and then the\n \n\nyou give your model and then the\nruntime. So like the guardrails like how\n\nruntime. So like the guardrails like how\n \n\nruntime. So like the guardrails like how\nyou do your execution environment. Um,\n\nyou do your execution environment. Um,\n \n\nyou do your execution environment. Um,\nand generally like when you're building\n\nand generally like when you're building\n \n\nand generally like when you're building\nvoice agents, that's all the same things\n\nvoice agents, that's all the same things\n \n\nvoice agents, that's all the same things\nyou should be worrying about, but\n\nyou should be worrying about, but\n \n\nyou should be worrying about, but\nthere's also a few other things that are\n\nthere's also a few other things that are\n \n\nthere's also a few other things that are\nmaybe a bit different that we're going\n\nmaybe a bit different that we're going\n \n\nmaybe a bit different that we're going\nto focus on today. Uh, so the main stuff\n\nto focus on today. Uh, so the main stuff\n \n\nto focus on today. Uh, so the main stuff\nis like your system design is probably a\n\nis like your system design is probably a\n \n\nis like your system design is probably a\nbit different than a traditional LM\n\nbit different than a traditional LM\n \n\nbit different than a traditional LM\nagent. Um, it's probably a bit different\n\nagent. Um, it's probably a bit different\n \n\nagent. Um, it's probably a bit different\non the prompting side and customization\n\non the prompting side and customization\n \n\non the prompting side and customization\nof the voice. Um, the tools you're using\n\nof the voice. Um, the tools you're using\n \n\nof the voice. Um, the tools you're using\nprobably a bit different. Um, and then\n\nprobably a bit different. Um, and then\n \n\nprobably a bit different. Um, and then\nalso eval guardrails you might have to\n\nalso eval guardrails you might have to\n \n\nalso eval guardrails you might have to\nthink about um, as well. So these are\n\nthink about um, as well. So these are\n \n\nthink about um, as well. So these are\nthe things we'll we'll probably focus on\n\nthe things we'll we'll probably focus on\n \n\nthe things we'll we'll probably focus on\nthat are like distinct when you're\n\nthat are like distinct when you're\n \n\nthat are like distinct when you're\nbuilding specifically voice agents\n\nbuilding specifically voice agents\n \n\nbuilding specifically voice agents\ncompared to like traditional agents. compared to like traditional agents. compared to like traditional agents. Cool. So if you've all built uh maybe\n\nCool. So if you've all built uh maybe\n \n\nCool. So if you've all built uh maybe\nlike a textbased agent, let's use like\n\nlike a textbased agent, let's use like\n \n\nlike a textbased agent, let's use like\ncustomer service as a conical example. customer service as a conical example. customer service as a conical example. Um you have like some user question. You\n\nUm you have like some user question. You\n \n\nUm you have like some user question. You\nhave some sort of triage agent that it's\n\nhave some sort of triage agent that it's\n \n\nhave some sort of triage agent that it's\nlike a small model that goes to other\n\nlike a small model that goes to other\n \n\nlike a small model that goes to other\nmodels here that will do like the harder\n\nmodels here that will do like the harder\n \n\nmodels here that will do like the harder\ntasks. So you have like an 03 to do like\n\ntasks. So you have like an 03 to do like\n \n\ntasks. So you have like an 03 to do like\nthe refund or maybe like an L4 mini to\n\nthe refund or maybe like an L4 mini to\n \n\nthe refund or maybe like an L4 mini to\ndo some of the cancellation. Um, and\n\ndo some of the cancellation. Um, and\n \n\ndo some of the cancellation. Um, and\ntypically that's like how you build a a\n\ntypically that's like how you build a a\n \n\ntypically that's like how you build a a\nnormal agent today. Uh, for voice, one\n\nnormal agent today. Uh, for voice, one\n \n\nnormal agent today. Uh, for voice, one\npattern that we're starting to see more\n\npattern that we're starting to see more\n \n\npattern that we're starting to see more\nand more of is some sort of like\n\nand more of is some sort of like\n \n\nand more of is some sort of like\ndelegation through tools. So you would\n\ndelegation through tools. So you would\n \n\ndelegation through tools. So you would\nhave like the real-time API be your like\n\nhave like the real-time API be your like\n \n\nhave like the real-time API be your like\nfrontline agent. So it does a lot of the\n\nfrontline agent. So it does a lot of the\n \n\nfrontline agent. So it does a lot of the\nnormal interaction patterns that you're\n\nnormal interaction patterns that you're\n \n\nnormal interaction patterns that you're\nused to. So it can respond to like the\n\nused to. So it can respond to like the\n \n\nused to. So it can respond to like the\neasy questions that you sort of want\n\neasy questions that you sort of want\n \n\neasy questions that you sort of want\nyour model to answer and you know you're\n\nyour model to answer and you know you're\n \n\nyour model to answer and you know you're\nconfident in your model answering. Um,\n\nconfident in your model answering. Um,\n \n\nconfident in your model answering. Um,\nbut then there's also other questions\n\nbut then there's also other questions\n \n\nbut then there's also other questions\nthat might be a bit harder. Um, and then\n\nthat might be a bit harder. Um, and then\n \n\nthat might be a bit harder. Um, and then\nyou want your model to like do a tool\n\nyou want your model to like do a tool\n \n\nyou want your model to like do a tool\ncall to these other agents that are run\n\ncall to these other agents that are run\n \n\ncall to these other agents that are run\nby smarter models behind the hood. Um,\n\nby smarter models behind the hood. Um,\n \n\nby smarter models behind the hood. Um,\nso that's a pattern that we'll show a\n\nso that's a pattern that we'll show a\n \n\nso that's a pattern that we'll show a\nquick video of of like how this would\n\nquick video of of like how this would\n \n\nquick video of of like how this would\nwork. >> I've authenticated you now. What item\n\n>> I've authenticated you now. What item\n \n\n>> I've authenticated you now. What item\nwould you like to return? would you like to return? would you like to return? >> Yeah, I want to return the snowboard I\n\n>> Yeah, I want to return the snowboard I\n \n\n>> Yeah, I want to return the snowboard I\nbought. bought. bought. >> Got it. I'm reviewing the policy and\n\n>> Got it. I'm reviewing the policy and\n \n\n>> Got it. I'm reviewing the policy and\nwe'll get back to you with next steps\n\nwe'll get back to you with next steps\n \n\nwe'll get back to you with next steps\nshortly. So, here's a scenario where\n\nshortly. So, here's a scenario where\n \n\nshortly. So, here's a scenario where\nwe're actually using like a much smaller\n\nwe're actually using like a much smaller\n \n\nwe're actually using like a much smaller\nmodel04 mini uh and delegating to that\n\nmodel04 mini uh and delegating to that\n \n\nmodel04 mini uh and delegating to that\nbecause we don't want uh a smaller\n\nbecause we don't want uh a smaller\n \n\nbecause we don't want uh a smaller\nmodel. model. model. >> It looks like the return you are making\n\n>> It looks like the return you are making\n \n\n>> It looks like the return you are making\nis within the 30-day return policy. We\n\nis within the 30-day return policy. We\n \n\nis within the 30-day return policy."
}
] |
[
{
"role": "system",
"content": "You are an AI Engineer content creator. Write in the style of Swyx and the Latent Space podcast - technical but accessible, with practical insights about AI engineering, agents, LLMs, and developer tools. Be direct, insightful, and focus on what matters to practitioners."
},
{
"role": "user",
"content": "Share your insights on this AI engineering topic:\n\nWe\nwill process the return and send you a\n\nwill process the return and send you a\n \n\nwill process the return and send you a\nconfirmation email with next steps\n\nconfirmation email with next steps\n \n\nconfirmation email with next steps\nshortly. >> So, that's like one pattern uh we've\n\n>> So, that's lik..."
},
{
"role": "assistant",
"content": "We\nwill process the return and send you a\n\nwill process the return and send you a\n \n\nwill process the return and send you a\nconfirmation email with next steps\n\nconfirmation email with next steps\n \n\nconfirmation email with next steps\nshortly. >> So, that's like one pattern uh we've\n\n>> So, that's like one pattern uh we've\n \n\n>> So, that's like one pattern uh we've\nseen on the architecture side. Another\n\nseen on the architecture side. Another\n \n\nseen on the architecture side. Another\npoint I touched on is like the the way\n\npoint I touched on is like the the way\n \n\npoint I touched on is like the the way\nyou basically customize your brand and\n\nyou basically customize your brand and\n \n\nyou basically customize your brand and\nwhat you're sort of building. Uh so the\n\nwhat you're sort of building. Uh so the\n \n\nwhat you're sort of building. Uh so the\nprompts you're using is a huge part of\n\nprompts you're using is a huge part of\n \n\nprompts you're using is a huge part of\nthat. And the way to think about this is\n\nthat. And the way to think about this is\n \n\nthat. And the way to think about this is\nwhen you're prompting models today uh in\n\nwhen you're prompting models today uh in\n \n\nwhen you're prompting models today uh in\nthe textbased world, you only can\n\nthe textbased world, you only can\n \n\nthe textbased world, you only can\ncontrol like the instructions you're\n\ncontrol like the instructions you're\n \n\ncontrol like the instructions you're\ngiving it and sort of what you want the\n\ngiving it and sort of what you want the\n \n\ngiving it and sort of what you want the\nmodel to do. But in voice based\n\nmodel to do. But in voice based\n \n\nmodel to do. But in voice based\napplications, you can also control the\n\napplications, you can also control the\n \n\napplications, you can also control the\nexpressiveness of the voice and how you\n\nexpressiveness of the voice and how you\n \n\nexpressiveness of the voice and how you\nwant the model to speak or sound. Uh, so\n\nwant the model to speak or sound. Uh, so\n \n\nwant the model to speak or sound. Uh, so\nthis is like an example prompt here of,\n\nthis is like an example prompt here of,\n \n\nthis is like an example prompt here of,\nhey, you can control like the demeanor,\n\nhey, you can control like the demeanor,\n \n\nhey, you can control like the demeanor,\nthe tone, the level of enthusiasm, all\n\nthe tone, the level of enthusiasm, all\n \n\nthe tone, the level of enthusiasm, all\nthose things that don't really get\n\nthose things that don't really get\n \n\nthose things that don't really get\ncaptured in a in a text agent that you\n\ncaptured in a in a text agent that you\n \n\ncaptured in a in a text agent that you\ndo have much more control over in a\n\ndo have much more control over in a\n \n\ndo have much more control over in a\nvoice space agent. Um, here's just a fun website you can\n\nUm, here's just a fun website you can\n \n\nUm, here's just a fun website you can\nuse to play around with this open. Um,\n\nuse to play around with this open. Um,\n \n\nuse to play around with this open. Um,\nwhere you can play around with different\n\nwhere you can play around with different\n \n\nwhere you can play around with different\nvoices and also click through sample\n\nvoices and also click through sample\n \n\nvoices and also click through sample\nprompts that we've created. Uh this is\n\nprompts that we've created. Uh this is\n \n\nprompts that we've created. Uh this is\njust a great place to get started on\n\njust a great place to get started on\n \n\njust a great place to get started on\nlike actually playing around with the\n\nlike actually playing around with the\n \n\nlike actually playing around with the\nexpressiveness of voices and seeing that\n\nexpressiveness of voices and seeing that\n \n\nexpressiveness of voices and seeing that\nthere is a ceiling and like a lot of\n\nthere is a ceiling and like a lot of\n \n\nthere is a ceiling and like a lot of\nfluctuation you can get in performance\n\nfluctuation you can get in performance\n \n\nfluctuation you can get in performance\njust by the prompts you do use. just by the prompts you do use. just by the prompts you do use. Uh, another side of this is when you're\n\nUh, another side of this is when you're\n \n\nUh, another side of this is when you're\nwhen you're prompting models in the the\n\nwhen you're prompting models in the the\n \n\nwhen you're prompting models in the the\ntextbased approach, you'll probably have\n\ntextbased approach, you'll probably have\n \n\ntextbased approach, you'll probably have\nlike a lot of few shot examples of like,\n\nlike a lot of few shot examples of like,\n \n\nlike a lot of few shot examples of like,\nhey, I want you to do these few steps uh\n\nhey, I want you to do these few steps uh\n \n\nhey, I want you to do these few steps uh\nand then do these next few steps um and\n\nand then do these next few steps um and\n \n\nand then do these next few steps um and\ngo through like a typical uh\n\ngo through like a typical uh\n \n\ngo through like a typical uh\nconversation flow. Uh the same thing you\n\nconversation flow. Uh the same thing you\n \n\nconversation flow. Uh the same thing you\ncan sort of mimic in voice. So if you\n\ncan sort of mimic in voice. So if you\n \n\ncan sort of mimic in voice. So if you\nsee in in this picture uh there's like\n\nsee in in this picture uh there's like\n \n\nsee in in this picture uh there's like\nsome ID of hey I want you to do some\n\nsome ID of hey I want you to do some\n \n\nsome ID of hey I want you to do some\ngreeting, the description of it and then\n\ngreeting, the description of it and then\n \n\ngreeting, the description of it and then\nthe instructions for the users. Um and\n\nthe instructions for the users. Um and\n \n\nthe instructions for the users. Um and\nyou can just go through that. So this is\n\nyou can just go through that. So this is\n \n\nyou can just go through that. So this is\nlike a sample way of you to think\n\nlike a sample way of you to think\n \n\nlike a sample way of you to think\nthrough how you should be prompting\n\nthrough how you should be prompting\n \n\nthrough how you should be prompting\nmodels especially for more complex tasks\n\nmodels especially for more complex tasks\n \n\nmodels especially for more complex tasks\nthat you want the real-time API to\n\nthat you want the real-time API to\n \n\nthat you want the real-time API to\nhandle. handle. handle. Uh the next big bucket of things that\n\nUh the next big bucket of things that\n \n\nUh the next big bucket of things that\nare sort of important or maybe like a\n\nare sort of important or maybe like a\n \n\nare sort of important or maybe like a\nbit different for the voice agents\n\nbit different for the voice agents\n \n\nbit different for the voice agents\nyou're building is tools. Tool use in\n\nyou're building is tools. Tool use in\n \n\nyou're building is tools. Tool use in\ngeneral is like very uh important\n\ngeneral is like very uh important\n \n\ngeneral is like very uh important\nbecause you want your model to connect\n\nbecause you want your model to connect\n \n\nbecause you want your model to connect\nto other things that are sort of\n\nto other things that are sort of\n \n\nto other things that are sort of\nimportant for you. Um and the first step\n\nimportant for you. Um and the first step\n \n\nimportant for you. Um and the first step\nis honestly just start simple. you don't\n\nis honestly just start simple. you don't\n \n\nis honestly just start simple. you don't\nneed to connect 10 tools or like 20\n\nneed to connect 10 tools or like 20\n \n\nneed to connect 10 tools or like 20\ntools to a given model. Uh keep the\n\ntools to a given model. Uh keep the\n \n\ntools to a given model. Uh keep the\nnumber of tool calls pretty limited for\n\nnumber of tool calls pretty limited for\n \n\nnumber of tool calls pretty limited for\na given agent. Uh and that maybe goes\n\na given agent. Uh and that maybe goes\n \n\na given agent. Uh and that maybe goes\nback to the first diagram we showed of\n\nback to the first diagram we showed of\n \n\nback to the first diagram we showed of\nyou want to delegate to different models\n\nyou want to delegate to different models\n \n\nyou want to delegate to different models\nor agents to do different tasks."
}
] |
[
{
"role": "system",
"content": "You are an AI Engineer content creator. Write in the style of Swyx and the Latent Space podcast - technical but accessible, with practical insights about AI engineering, agents, LLMs, and developer tools. Be direct, insightful, and focus on what matters to practitioners."
},
{
"role": "user",
"content": "Share your insights on this AI engineering topic:\n\nSo here\n\nor agents to do different tasks. So here\n \n\nor agents to do different tasks. So here\na given agent don't give it a ton of\n\na given agent don't give it a ton of\n \n\na given agent don't give it a ton of\ntools to start with and then slowly add\n\ntools to start with and then slowly add\n \n\ntools t..."
},
{
"role": "assistant",
"content": "So here\n\nor agents to do different tasks. So here\n \n\nor agents to do different tasks. So here\na given agent don't give it a ton of\n\na given agent don't give it a ton of\n \n\na given agent don't give it a ton of\ntools to start with and then slowly add\n\ntools to start with and then slowly add\n \n\ntools to start with and then slowly add\non more tools as needed. Um handoffs. So\n\non more tools as needed. Um handoffs. So\n \n\non more tools as needed. Um handoffs. So\nif you ever you uh use the agents SDK,\n\nif you ever you uh use the agents SDK,\n \n\nif you ever you uh use the agents SDK,\nthis is a concept of if we have a given\n\nthis is a concept of if we have a given\n \n\nthis is a concept of if we have a given\nmodel um you want to pass it to another\n\nmodel um you want to pass it to another\n \n\nmodel um you want to pass it to another\num and here you can manage context\n\num and here you can manage context\n \n\num and here you can manage context\nbetween handoffs as well. So the thing\n\nbetween handoffs as well. So the thing\n \n\nbetween handoffs as well. So the thing\nto remember here is you might have a\n\nto remember here is you might have a\n \n\nto remember here is you might have a\ngiven agent and you're going to another\n\ngiven agent and you're going to another\n \n\ngiven agent and you're going to another\none but you want to keep the context the\n\none but you want to keep the context the\n \n\none but you want to keep the context the\nsame between them. Um so a good pattern\n\nsame between them. Um so a good pattern\n \n\nsame between them. Um so a good pattern\nto do is actually summarizing the\n\nto do is actually summarizing the\n \n\nto do is actually summarizing the\nconversation state and then passing it\n\nconversation state and then passing it\n \n\nconversation state and then passing it\nto the other agents so you don't lose\n\nto the other agents so you don't lose\n \n\nto the other agents so you don't lose\nany of the the context and it's not\n\nany of the the context and it's not\n \n\nany of the the context and it's not\nlossy. Uh a final one is delegation. So\n\nlossy. Uh a final one is delegation. So\n \n\nlossy. Uh a final one is delegation. So\nthe concept we showed a bit earlier of\n\nthe concept we showed a bit earlier of\n \n\nthe concept we showed a bit earlier of\nlike using 03 mini or 04 mini to do the\n\nlike using 03 mini or 04 mini to do the\n \n\nlike using 03 mini or 04 mini to do the\ntool call that's like natively built\n\ntool call that's like natively built\n \n\ntool call that's like natively built\ninto the agents SDK if you'd like to try\n\ninto the agents SDK if you'd like to try\n \n\ninto the agents SDK if you'd like to try\nit out. it out. it out. >> Um evals. So I think this is a pretty\n\n>> Um evals. So I think this is a pretty\n \n\n>> Um evals. So I think this is a pretty\nbig part of the like voice experience\n\nbig part of the like voice experience\n \n\nbig part of the like voice experience\nand maybe like breaking it down into\n\nand maybe like breaking it down into\n \n\nand maybe like breaking it down into\nlike four key buckets. I think the first\n\nlike four key buckets. I think the first\n \n\nlike four key buckets. I think the first\nand most obvious thing is always start\n\nand most obvious thing is always start\n \n\nand most obvious thing is always start\nwith observability. um you're not going\n\nwith observability. um you're not going\n \n\nwith observability. um you're not going\nto get very far if you don't know how\n\nto get very far if you don't know how\n \n\nto get very far if you don't know how\nyour data looks. Um so just make sure\n\nyour data looks. Um so just make sure\n \n\nyour data looks. Um so just make sure\nyou have traces of what's going on with\n\nyou have traces of what's going on with\n \n\nyou have traces of what's going on with\nyour agents uh the audio and everything\n\nyour agents uh the audio and everything\n \n\nyour agents uh the audio and everything\nso you can actually look at it and take\n\nso you can actually look at it and take\n \n\nso you can actually look at it and take\nactions. Um and the next thing is when\n\nactions. Um and the next thing is when\n \n\nactions. Um and the next thing is when\nyou're actually starting to do evals\n\nyou're actually starting to do evals\n \n\nyou're actually starting to do evals\nlike the most important thing is\n\nlike the most important thing is\n \n\nlike the most important thing is\nactually havememes to label these data\n\nactually havememes to label these data\n \n\nactually havememes to label these data\num and actually go and iterate on\n\num and actually go and iterate on\n \n\num and actually go and iterate on\nprompts from there. It sounds maybe a\n\nprompts from there. It sounds maybe a\n \n\nprompts from there. It sounds maybe a\nbit too easy or it's like not the most\n\nbit too easy or it's like not the most\n \n\nbit too easy or it's like not the most\nappropriate or uh maybe the best\n\nappropriate or uh maybe the best\n \n\nappropriate or uh maybe the best\napproach but it is the most effective\n\napproach but it is the most effective\n \n\napproach but it is the most effective\nthat we've seen when working with\n\nthat we've seen when working with\n \n\nthat we've seen when working with\ncustomers. Um it lets you go a lot\n\ncustomers. Um it lets you go a lot\n \n\ncustomers. Um it lets you go a lot\nfaster. Uh and then from there the next\n\nfaster. Uh and then from there the next\n \n\nfaster. Uh and then from there the next\nstep is transcription based evals. So\n\nstep is transcription based evals. So\n \n\nstep is transcription based evals. So\nthis is where you would have your\n\nthis is where you would have your\n \n\nthis is where you would have your\ntraditional as a judge evals or like\n\ntraditional as a judge evals or like\n \n\ntraditional as a judge evals or like\ntesting your function calling\n\ntesting your function calling\n \n\ntesting your function calling\nperformance on certain business criteria\n\nperformance on certain business criteria\n \n\nperformance on certain business criteria\nand having a rubric in place. Um, and\n\nand having a rubric in place. Um, and\n \n\nand having a rubric in place. Um, and\nthen there's this next bucket, uh, where\n\nthen there's this next bucket, uh, where\n \n\nthen there's this next bucket, uh, where\na lot of people ask us, how do we\n\na lot of people ask us, how do we\n \n\na lot of people ask us, how do we\nactually test the audio that's\n\nactually test the audio that's\n \n\nactually test the audio that's\ngenerated? Um, and for the most part,\n\ngenerated? Um, and for the most part,\n \n\ngenerated? Um, and for the most part,\nit's there's not a lot of things that\n\nit's there's not a lot of things that\n \n\nit's there's not a lot of things that\naudio uh, evals get you that maybe text\n\naudio uh, evals get you that maybe text\n \n\naudio uh, evals get you that maybe text\nevals don't, but the things that maybe\n\nevals don't, but the things that maybe\n \n\nevals don't, but the things that maybe\nit does get you is like understanding\n\nit does get you is like understanding\n \n\nit does get you is like understanding\nthe tone, understanding the pacing, or\n\nthe tone, understanding the pacing, or\n \n\nthe tone, understanding the pacing, or\nother things that are maybe a bit harder\n\nother things that are maybe a bit harder\n \n\nother things that are maybe a bit harder\nto capture just through text. And this\n\nto capture just through text. And this\n \n\nto capture just through text. And this\nis where you can use like a completions\n\nis where you can use like a completions\n \n\nis where you can use like a completions\nmodel or some other audio model. Uh so\n\nmodel or some other audio model. Uh so\n \n\nmodel or some other audio model. Uh so\nfor example GT4 audio to like understand\n\nfor example GT4 audio to like understand\n \n\nfor example GT4 audio to like understand\nthe tone, the pacing and what other\n\nthe tone, the pacing and what other\n \n\nthe tone, the pacing and what other\nintonations that you care about for your\n\nintonations that you care about for your\n \n\nintonations that you care about for your\nbusiness."
}
] |
[
{
"role": "system",
"content": "You are an AI Engineer content creator. Write in the style of Swyx and the Latent Space podcast - technical but accessible, with practical insights about AI engineering, agents, LLMs, and developer tools. Be direct, insightful, and focus on what matters to practitioners."
},
{
"role": "user",
"content": "Share your insights on this AI engineering topic:\n\nUm and then the final one that\n\nbusiness. Um and then the final one that\n \n\nbusiness. Um and then the final one that\nwe've started to see a bit more is\n\nwe've started to see a bit more is\n \n\nwe've started to see a bit more is\nactually synthetic conversations. So for\n\nactually synthetic conversations..."
},
{
"role": "assistant",
"content": "Um and then the final one that\n\nbusiness. Um and then the final one that\n \n\nbusiness. Um and then the final one that\nwe've started to see a bit more is\n\nwe've started to see a bit more is\n \n\nwe've started to see a bit more is\nactually synthetic conversations. So for\n\nactually synthetic conversations. So for\n \n\nactually synthetic conversations. So for\nexample, maybe you have two real-time\n\nexample, maybe you have two real-time\n \n\nexample, maybe you have two real-time\nclients going back and forth across to\n\nclients going back and forth across to\n \n\nclients going back and forth across to\neach other. So maybe one is your\n\neach other. So maybe one is your\n \n\neach other. So maybe one is your\nreal-time API agent or whatever and then\n\nreal-time API agent or whatever and then\n \n\nreal-time API agent or whatever and then\nthe other is a set of customer personas\n\nthe other is a set of customer personas\n \n\nthe other is a set of customer personas\nthat you have and you can simulate like\n\nthat you have and you can simulate like\n \n\nthat you have and you can simulate like\nmany many of those conversations and\n\nmany many of those conversations and\n \n\nmany many of those conversations and\nthen extract those evals across maybe\n\nthen extract those evals across maybe\n \n\nthen extract those evals across maybe\nlike transcriptions or audio and then\n\nlike transcriptions or audio and then\n \n\nlike transcriptions or audio and then\nhave a much better way to understand\n\nhave a much better way to understand\n \n\nhave a much better way to understand\nwhat you've sort of built. what you've sort of built. what you've sort of built. Cool. Uh and then the final thing here\n\nCool. Uh and then the final thing here\n \n\nCool. Uh and then the final thing here\nis guardrails. Um because especially for\n\nis guardrails. Um because especially for\n \n\nis guardrails. Um because especially for\nthe real-time API it's pretty fast. uh\n\nthe real-time API it's pretty fast. uh\n \n\nthe real-time API it's pretty fast. uh\nyou want to have guardrails that make\n\nyou want to have guardrails that make\n \n\nyou want to have guardrails that make\nsure that you have the safety that's\n\nsure that you have the safety that's\n \n\nsure that you have the safety that's\nneeded for uh to actually have\n\nneeded for uh to actually have\n \n\nneeded for uh to actually have\nconfidence in in the solution you're\n\nconfidence in in the solution you're\n \n\nconfidence in in the solution you're\nyou're rolling out to users. Um so the\n\nyou're rolling out to users. Um so the\n \n\nyou're rolling out to users. Um so the\nmain things we have here is like run\n\nmain things we have here is like run\n \n\nmain things we have here is like run\nthem async uh generally because the\n\nthem async uh generally because the\n \n\nthem async uh generally because the\ngenerated text from the real-time API is\n\ngenerated text from the real-time API is\n \n\ngenerated text from the real-time API is\nmuch faster than the spoken audio that\n\nmuch faster than the spoken audio that\n \n\nmuch faster than the spoken audio that\nyou get back from the model. So you have\n\nyou get back from the model. So you have\n \n\nyou get back from the model. So you have\nroom to play with the latency here. Uh\n\nroom to play with the latency here. Uh\n \n\nroom to play with the latency here. Uh\nthe next thing also is you have control\n\nthe next thing also is you have control\n \n\nthe next thing also is you have control\nto set like whatever debounce period you\n\nto set like whatever debounce period you\n \n\nto set like whatever debounce period you\nhave here. So in the code snippet uh to\n\nhave here. So in the code snippet uh to\n \n\nhave here. So in the code snippet uh to\nthe right hand side of the screen you'll\n\nthe right hand side of the screen you'll\n \n\nthe right hand side of the screen you'll\nsee that like right now it runs every\n\nsee that like right now it runs every\n \n\nsee that like right now it runs every\n100 characters to run the guardrails but\n\n100 characters to run the guardrails but\n \n\n100 characters to run the guardrails but\nyou can control that if you want to. you can control that if you want to. you can control that if you want to. Awesome. And then maybe just some\n\nAwesome. And then maybe just some\n \n\nAwesome. And then maybe just some\nlearnings that we've seen from other\n\nlearnings that we've seen from other\n \n\nlearnings that we've seen from other\nfolks in the field. Um Lemonade so uh AI\n\nfolks in the field. Um Lemonade so uh AI\n \n\nfolks in the field. Um Lemonade so uh AI\nlike insurance company they're like\n\nlike insurance company they're like\n \n\nlike insurance company they're like\nbuilding e one of the things we like\n\nbuilding e one of the things we like\n \n\nbuilding e one of the things we like\nnoticed from them that made them\n\nnoticed from them that made them\n \n\nnoticed from them that made them\nsuccessful is they like focused really\n\nsuccessful is they like focused really\n \n\nsuccessful is they like focused really\nearly on eval guardrails and like\n\nearly on eval guardrails and like\n \n\nearly on eval guardrails and like\nfeedback mechanisms for their team. And\n\nfeedback mechanisms for their team. And\n \n\nfeedback mechanisms for their team. And\neven if it wasn't scalable, they\n\neven if it wasn't scalable, they\n \n\neven if it wasn't scalable, they\nrealized that and it actually made them\n\nrealized that and it actually made them\n \n\nrealized that and it actually made them\nmove a lot faster in the end. Um, and\n\nmove a lot faster in the end. Um, and\n \n\nmove a lot faster in the end. Um, and\nthen finally for Tinder, um, they\n\nthen finally for Tinder, um, they\n \n\nthen finally for Tinder, um, they\nrealized that customization and brand\n\nrealized that customization and brand\n \n\nrealized that customization and brand\nrealism was pretty important for them\n\nrealism was pretty important for them\n \n\nrealism was pretty important for them\nwhen they were launching their RZ chat\n\nwhen they were launching their RZ chat\n \n\nwhen they were launching their RZ chat\nexperience. Um, so that's what they\n\nexperience. Um, so that's what they\n \n\nexperience. Um, so that's what they\nfocused on and it created a much better\n\nfocused on and it created a much better\n \n\nfocused on and it created a much better\nexperience for their users. experience for their users. experience for their users. And now I'll hand it off to Toki to\n\nAnd now I'll hand it off to Toki to\n \n\nAnd now I'll hand it off to Toki to\n>> Yeah, just to wrap us all up. So I kind\n\n>> Yeah, just to wrap us all up. So I kind\n \n\n>> Yeah, just to wrap us all up. So I kind\nof what I said in the beginning is we're\n\nof what I said in the beginning is we're\n \n\nof what I said in the beginning is we're\nreally entering this multimodal era. So\n\nreally entering this multimodal era. So\n \n\nreally entering this multimodal era. So\naway from or in addition to textbased\n\naway from or in addition to textbased\n \n\naway from or in addition to textbased\nmodels, we have now obviously um video\n\nmodels, we have now obviously um video\n \n\nmodels, we have now obviously um video\nand image models, but now audio. So very\n\nand image models, but now audio. So very\n \n\nand image models, but now audio. So very\nmuch in the multimodal era and this\n\nmuch in the multimodal era and this\n \n\nmuch in the multimodal era and this\nreal-time speech to speech technology is\n\nreal-time speech to speech technology is\n \n\nreal-time speech to speech technology is\nemerging. And I think we had a kind of\n\nemerging. And I think we had a kind of\n \n\nemerging. And I think we had a kind of\nlowkey update yesterday, a real time\n\nlowkey update yesterday, a real time\n \n\nlowkey update yesterday, a real time\nAPI. We had a new snapshot that we that\n\nAPI. We had a new snapshot that we that\n \n\nAPI. We had a new snapshot that we that\nwe released that's actually a lot\n\nwe released that's actually a lot\n \n\nwe released that's actually a lot\nbetter. So I really feel like now is the\n\nbetter. So I really feel like now is the\n \n\nbetter. So I really feel like now is the\ntime to to build. So you kind of have\n\ntime to to build. So you kind of have\n \n\ntime to to build. So you kind of have\nthis first mover's advantage to to build\n\nthis first mover's advantage to to build\n \n\nthis first mover's advantage to to build\nnow. I think the technology is getting\n\nnow."
}
] |
[
{
"role": "system",
"content": "You are an AI Engineer content creator. Write in the style of Swyx and the Latent Space podcast - technical but accessible, with practical insights about AI engineering, agents, LLMs, and developer tools. Be direct, insightful, and focus on what matters to practitioners."
},
{
"role": "user",
"content": "Share your insights on this AI engineering topic:\n\nI think the technology is getting\n \n\nnow. I think the technology is getting\nto that point where it is good enough to\n\nto that point where it is good enough to\n \n\nto that point where it is good enough to\nbuild scalable production applications. build scalable production applications. build scalable pr..."
},
{
"role": "assistant",
"content": "I think the technology is getting\n \n\nnow. I think the technology is getting\nto that point where it is good enough to\n\nto that point where it is good enough to\n \n\nto that point where it is good enough to\nbuild scalable production applications. build scalable production applications. build scalable production applications. Um, so really excited to see what you\n\nUm, so really excited to see what you\n \n\nUm, so really excited to see what you\nall build. Please test it out. Um, we'll\n\nall build. Please test it out. Um, we'll\n \n\nall build. Please test it out. Um, we'll\nbe around after the talk if you guys\n\nbe around after the talk if you guys\n \n\nbe around after the talk if you guys\nhave any questions, but thanks for the\n\nhave any questions, but thanks for the\n \n\nhave any questions, but thanks for the\ntime. [Music]"
}
] |
[
{
"role": "system",
"content": "You are an AI Engineer content creator. Write in the style of Swyx and the Latent Space podcast - technical but accessible, with practical insights about AI engineering, agents, LLMs, and developer tools. Be direct, insightful, and focus on what matters to practitioners."
},
{
"role": "user",
"content": "Share your insights on this AI engineering topic:\n\n[Music]\n\n \n\nWelcome everyone. Welcome everyone. Welcome everyone. I'm going to talk about practical\n\nI'm going to talk about practical\n \n\nI'm going to talk about practical\ntactics to build uh reliable AI\n\ntactics to build uh reliable AI\n \n\ntactics to build uh reliable AI\napplications and why nobody ..."
},
{
"role": "assistant",
"content": "[Music]\n\n \n\nWelcome everyone. Welcome everyone. Welcome everyone. I'm going to talk about practical\n\nI'm going to talk about practical\n \n\nI'm going to talk about practical\ntactics to build uh reliable AI\n\ntactics to build uh reliable AI\n \n\ntactics to build uh reliable AI\napplications and why nobody does it this\n\napplications and why nobody does it this\n \n\napplications and why nobody does it this\nway yet. way yet. way yet. Uh a little bit about myself or why you\n\nUh a little bit about myself or why you\n \n\nUh a little bit about myself or why you\nshould trust me. Uh I have allowed 15\n\nshould trust me. Uh I have allowed 15\n \n\nshould trust me. Uh I have allowed 15\nyears as a startup co-founder and CTO. years as a startup co-founder and CTO. years as a startup co-founder and CTO. Uh I held executive positions for the\n\nUh I held executive positions for the\n \n\nUh I held executive positions for the\nlast five years at uh several\n\nlast five years at uh several\n \n\nlast five years at uh several\nenterprises. uh but most importantly I\n\nenterprises. uh but most importantly I\n \n\nenterprises. uh but most importantly I\nspent last couple of years developing\n\nspent last couple of years developing\n \n\nspent last couple of years developing\na lot of gen projects ranging from PC's\n\na lot of gen projects ranging from PC's\n \n\na lot of gen projects ranging from PC's\nto uh many production level uh solutions\n\nto uh many production level uh solutions\n \n\nto uh many production level uh solutions\nand helped some companies to get it done\n\nand helped some companies to get it done\n \n\nand helped some companies to get it done\nand uh I've learned or distilled a way\n\nand uh I've learned or distilled a way\n \n\nand uh I've learned or distilled a way\nto uh make these applications reliable\n\nto uh make these applications reliable\n \n\nto uh make these applications reliable\nand there are quite a lot of uh tracks\n\nand there are quite a lot of uh tracks\n \n\nand there are quite a lot of uh tracks\nthis uh uh this conference about evals\n\nthis uh uh this conference about evals\n \n\nthis uh uh this conference about evals\nand reliability but uh to my surprise\n\nand reliability but uh to my surprise\n \n\nand reliability but uh to my surprise\nnobody was talking about the most\n\nnobody was talking about the most\n \n\nnobody was talking about the most\nimportant things and uh we're going to\n\nimportant things and uh we're going to\n \n\nimportant things and uh we're going to\ntalk about it right now. talk about it right now. talk about it right now. So uh standard software development life\n\nSo uh standard software development life\n \n\nSo uh standard software development life\ncycle is uh very standard uh simple uh\n\ncycle is uh very standard uh simple uh\n \n\ncycle is uh very standard uh simple uh\nyou design your solution, you develop\n\nyou design your solution, you develop\n \n\nyou design your solution, you develop\nit, you test it and then eventually you\n\nit, you test it and then eventually you\n \n\nit, you test it and then eventually you\ndeploy it. And uh when people start\n\ndeploy it. And uh when people start\n \n\ndeploy it. And uh when people start\ndoing uh PC with AI\n\ndoing uh PC with AI\n \n\ndoing uh PC with AI\nit sounds simple like you can very\n\nit sounds simple like you can very\n \n\nit sounds simple like you can very\neasily do you have some prompt and uh\n\neasily do you have some prompt and uh\n \n\neasily do you have some prompt and uh\nmodels are very capable but then you\n\nmodels are very capable but then you\n \n\nmodels are very capable but then you\nstart uh facing some uh unexpected\n\nstart uh facing some uh unexpected\n \n\nstart uh facing some uh unexpected\nchallenges\n\nchallenges\n \n\nchallenges\nuh actually like you can easily do a PC\n\nuh actually like you can easily do a PC\n \n\nuh actually like you can easily do a PC\nthat works 50% of the time uh but we're\n\nthat works 50% of the time uh but we're\n \n\nthat works 50% of the time uh but we're\nlike making it do the same reliable work\n\nlike making it do the same reliable work\n \n\nlike making it do the same reliable work\nthe Rest of the 50% is very hard uh\n\nthe Rest of the 50% is very hard uh\n \n\nthe Rest of the 50% is very hard uh\nbecause models are nondeterministic\n\nbecause models are nondeterministic\n \n\nbecause models are nondeterministic\nand uh it starts requiring uh a data\n\nand uh it starts requiring uh a data\n \n\nand uh it starts requiring uh a data\nscience approach uh continuous\n\nscience approach uh continuous\n \n\nscience approach uh continuous\nexperimentation you need to try this\n\nexperimentation you need to try this\n \n\nexperimentation you need to try this\nprompt you need to try that model you\n\nprompt you need to try that model you\n \n\nprompt you need to try that model you\nneed to try this approach etc etc and uh\n\nneed to try this approach etc etc and uh\n \n\nneed to try this approach etc etc and uh\neverything in your solution everything\n\neverything in your solution everything\n \n\neverything in your solution everything\nthat uh represents your solution which\n\nthat uh represents your solution which\n \n\nthat uh represents your solution which\nis your code your logic uh the prompts\n\nis your code your logic uh the prompts\n \n\nis your code your logic uh the prompts\nthat you use the the models that you use\n\nthat you use the the models that you use\n \n\nthat you use the the models that you use\nthe the data that you base your solution\n\nthe the data that you base your solution\n \n\nthe the data that you base your solution\non changing anything of that impacts\n\non changing anything of that impacts\n \n\non changing anything of that impacts\nyour uh solution in unexpected ways. Um people very often come to this uh to\n\nUm people very often come to this uh to\n \n\nUm people very often come to this uh to\ntry solving this with the wrong\n\ntry solving this with the wrong\n \n\ntry solving this with the wrong\napproach. They start with a data science\n\napproach. They start with a data science\n \n\napproach. They start with a data science\nmetrics. They like it sounds reasonable,\n\nmetrics. They like it sounds reasonable,\n \n\nmetrics. They like it sounds reasonable,\nright? So it requires data science\n\nright? So it requires data science\n \n\nright? So it requires data science\napproach of experimentation and uh\n\napproach of experimentation and uh\n \n\napproach of experimentation and uh\npeople start measuring groundness,\n\npeople start measuring groundness,\n \n\npeople start measuring groundness,\nfactuality, bias and other uh metrics\n\nfactuality, bias and other uh metrics\n \n\nfactuality, bias and other uh metrics\nthat don't really help you to understand\n\nthat don't really help you to understand\n \n\nthat don't really help you to understand\nuh is your solution uh working the right\n\nuh is your solution uh working the right\n \n\nuh is your solution uh working the right\nway? Does it uh does your latest change\n\nway? Does it uh does your latest change\n \n\nway? Does it uh does your latest change\nimproved uh your solution in the right\n\nimproved uh your solution in the right\n \n\nimproved uh your solution in the right\nway for your users? uh for example I've\n\nway for your users? uh for example I've\n \n\nway for your users?"
}
] |
[
{
"role": "system",
"content": "You are an AI Engineer content creator. Write in the style of Swyx and the Latent Space podcast - technical but accessible, with practical insights about AI engineering, agents, LLMs, and developer tools. Be direct, insightful, and focus on what matters to practitioners."
},
{
"role": "user",
"content": "Share your insights on this AI engineering topic:\n\nuh for example I've\nbeen talking to an ex-colague that are\n\nbeen talking to an ex-colague that are\n \n\nbeen talking to an ex-colague that are\nbuilding a customer support bot at\n\nbuilding a customer support bot at\n \n\nbuilding a customer support bot at\ntweaks I asked him how do you know that\n\ntweaks I ..."
},
{
"role": "assistant",
"content": "uh for example I've\nbeen talking to an ex-colague that are\n\nbeen talking to an ex-colague that are\n \n\nbeen talking to an ex-colague that are\nbuilding a customer support bot at\n\nbuilding a customer support bot at\n \n\nbuilding a customer support bot at\ntweaks I asked him how do you know that\n\ntweaks I asked him how do you know that\n \n\ntweaks I asked him how do you know that\nyour solution is working well he started\n\nyour solution is working well he started\n \n\nyour solution is working well he started\ntalking about factuality and other data\n\ntalking about factuality and other data\n \n\ntalking about factuality and other data\nscience metrics\n\nscience metrics\n \n\nscience metrics\nu that's again I started to dig deeper\n\nu that's again I started to dig deeper\n \n\nu that's again I started to dig deeper\nand then we just uh together figure out\n\nand then we just uh together figure out\n \n\nand then we just uh together figure out\nthat the most important metric for them\n\nthat the most important metric for them\n \n\nthat the most important metric for them\nis uh the rate of moving from AI I\n\nis uh the rate of moving from AI I\n \n\nis uh the rate of moving from AI I\nsupport bot like escalation to a human\n\nsupport bot like escalation to a human\n \n\nsupport bot like escalation to a human\nsupport. support. support. If uh your solution uh hasn't able to\n\nIf uh your solution uh hasn't able to\n \n\nIf uh your solution uh hasn't able to\nanswer the user with all this factuality\n\nanswer the user with all this factuality\n \n\nanswer the user with all this factuality\nlike it could be super grounded but\n\nlike it could be super grounded but\n \n\nlike it could be super grounded but\nstill not provide the right answer that\n\nstill not provide the right answer that\n \n\nstill not provide the right answer that\nthe user expects and uh this is what you\n\nthe user expects and uh this is what you\n \n\nthe user expects and uh this is what you\nactually need to test. actually need to test. actually need to test. Um and my experience was to start with\n\nUm and my experience was to start with\n \n\nUm and my experience was to start with\nreal world scenarios. So basically you\n\nreal world scenarios. So basically you\n \n\nreal world scenarios. So basically you\nneed to reverse engineer your metrics\n\nneed to reverse engineer your metrics\n \n\nneed to reverse engineer your metrics\nand your metrics should be very very\n\nand your metrics should be very very\n \n\nand your metrics should be very very\nspecific to what your end goal. So they\n\nspecific to what your end goal. So they\n \n\nspecific to what your end goal. So they\nshould come from a product experience\n\nshould come from a product experience\n \n\nshould come from a product experience\nfrom business outcomes. Uh if your\n\nfrom business outcomes. Uh if your\n \n\nfrom business outcomes. Uh if your\nsolution is customer support bot, you\n\nsolution is customer support bot, you\n \n\nsolution is customer support bot, you\nneed to figure out what your users want\n\nneed to figure out what your users want\n \n\nneed to figure out what your users want\nand uh how you can mimic it. And instead\n\nand uh how you can mimic it. And instead\n \n\nand uh how you can mimic it. And instead\nof measuring something u average or\n\nof measuring something u average or\n \n\nof measuring something u average or\nsomething generic, you need to measure a\n\nsomething generic, you need to measure a\n \n\nsomething generic, you need to measure a\nvery specific criterias. very specific criterias. very specific criterias. Uh cuz universal valves don't really\n\nUh cuz universal valves don't really\n \n\nUh cuz universal valves don't really\nwork. work. work. How do we do it? Uh so for example,\n\nHow do we do it? Uh so for example,\n \n\nHow do we do it? Uh so for example,\ncustomer support bot, which is by the\n\ncustomer support bot, which is by the\n \n\ncustomer support bot, which is by the\nway one of the hardest uh things to do\n\nway one of the hardest uh things to do\n \n\nway one of the hardest uh things to do\nproperly. uh let's say I have a bank and\n\nproperly. uh let's say I have a bank and\n \n\nproperly. uh let's say I have a bank and\nuh bank has FAQ materials\n\nuh bank has FAQ materials\n \n\nuh bank has FAQ materials\nwhich contain including like how do you\n\nwhich contain including like how do you\n \n\nwhich contain including like how do you\nreset your password? reset your password? reset your password? Um so what I usually do when I help my\n\nUm so what I usually do when I help my\n \n\nUm so what I usually do when I help my\nuh like companies that I help them to\n\nuh like companies that I help them to\n \n\nuh like companies that I help them to\nbuild uh AI solutions we start with uh\n\nbuild uh AI solutions we start with uh\n \n\nbuild uh AI solutions we start with uh\nreverse engineering like how do we\n\nreverse engineering like how do we\n \n\nreverse engineering like how do we\ncreate the valves based on that. So in\n\ncreate the valves based on that. So in\n \n\ncreate the valves based on that. So in\nthis case I use LLM and in most cases I\n\nthis case I use LLM and in most cases I\n \n\nthis case I use LLM and in most cases I\nuse LLM to come up with right\n\nuse LLM to come up with right\n \n\nuse LLM to come up with right\nevaluations. So here I can take say 01\n\nevaluations. So here I can take say 01\n \n\nevaluations. So here I can take say 01\nuh 03 now uh and just reverse engineer\n\nuh 03 now uh and just reverse engineer\n \n\nuh 03 now uh and just reverse engineer\nwhat should be the user question uh that\n\nwhat should be the user question uh that\n \n\nwhat should be the user question uh that\nwe know to answer based on these\n\nwe know to answer based on these\n \n\nwe know to answer based on these\nmaterials and what should be the\n\nmaterials and what should be the\n \n\nmaterials and what should be the\nspecific criteria that uh these\n\nspecific criteria that uh these\n \n\nspecific criteria that uh these\nmaterials are providing an answer for\n\nmaterials are providing an answer for\n \n\nmaterials are providing an answer for\nand some of these criteria are quite\n\nand some of these criteria are quite\n \n\nand some of these criteria are quite\nimportant. So for example here it says\n\nimportant. So for example here it says\n \n\nimportant. So for example here it says\nthat uh uh as part of the thing you you\n\nthat uh uh as part of the thing you you\n \n\nthat uh uh as part of the thing you you\nneed to receive a mobile validation. So\n\nneed to receive a mobile validation. So\n \n\nneed to receive a mobile validation. So\nyou receive a SMS code and uh it says\n\nyou receive a SMS code and uh it says\n \n\nyou receive a SMS code and uh it says\nthat if you uh don't have a mobile\n\nthat if you uh don't have a mobile\n \n\nthat if you uh don't have a mobile\nnumber then you can reach uh support etc\n\nnumber then you can reach uh support etc\n \n\nnumber then you can reach uh support etc\netc. Uh if some of that information is\n\netc. Uh if some of that information is\n \n\netc. Uh if some of that information is\nmissing from the answer the answer would\n\nmissing from the answer the answer would\n \n\nmissing from the answer the answer would\nnot be correct. not be correct. not be correct. You need to be very specific about what\n\nYou need to be very specific about what\n \n\nYou need to be very specific about what\nexact information you need to see in the\n\nexact information you need to see in the\n \n\nexact information you need to see in the\nanswer and that information is very\n\nanswer and that information is very\n \n\nanswer and that information is very\nspecific to that specific question. So\n\nspecific to that specific question. So\n \n\nspecific to that specific question. So\nyou need to build like lots of evals\n\nyou need to build like lots of evals\n \n\nyou need to build like lots of evals\nuh from the materials in this case uh\n\nuh from the materials in this case uh\n \n\nuh from the materials in this case uh\nthat mimic specific user questions that\n\nthat mimic specific user questions that\n \n\nthat mimic specific user questions that\nuh you need to be able to answer for. Uh\n\nuh you need to be able to answer for."
}
] |
[
{
"role": "system",
"content": "You are an AI Engineer content creator. Write in the style of Swyx and the Latent Space podcast - technical but accessible, with practical insights about AI engineering, agents, LLMs, and developer tools. Be direct, insightful, and focus on what matters to practitioners."
},
{
"role": "user",
"content": "Share your insights on this AI engineering topic:\n\nUh\n \n\nuh you need to be able to answer for. Uh\nhow do we do it? Usually again I work\n\nhow do we do it? Usually again I work\n \n\nhow do we do it? Usually again I work\nwith uh smart models like O3 uh and I uh\n\nwith uh smart models like O3 uh and I uh\n \n\nwith uh smart models like O3 uh and I uh\nprovided..."
},
{
"role": "assistant",
"content": "Uh\n \n\nuh you need to be able to answer for. Uh\nhow do we do it? Usually again I work\n\nhow do we do it? Usually again I work\n \n\nhow do we do it? Usually again I work\nwith uh smart models like O3 uh and I uh\n\nwith uh smart models like O3 uh and I uh\n \n\nwith uh smart models like O3 uh and I uh\nprovided enough context. I provided\n\nprovided enough context. I provided\n \n\nprovided enough context. I provided\nwhich personas are we trying to\n\nwhich personas are we trying to\n \n\nwhich personas are we trying to\nrepresent because you can make ask the\n\nrepresent because you can make ask the\n \n\nrepresent because you can make ask the\nsame question in uh completely different\n\nsame question in uh completely different\n \n\nsame question in uh completely different\nways depending on who is the persona\n\nways depending on who is the persona\n \n\nways depending on who is the persona\nasking uh yet you would expect exactly\n\nasking uh yet you would expect exactly\n \n\nasking uh yet you would expect exactly\nthe same answer. So you need to account\n\nthe same answer. So you need to account\n \n\nthe same answer. So you need to account\nfor it. for it. for it. Um so this is uh an example from uh the\n\nUm so this is uh an example from uh the\n \n\nUm so this is uh an example from uh the\nopen source platform that we have that\n\nopen source platform that we have that\n \n\nopen source platform that we have that\nuh just helps to get it done. So if you\n\nuh just helps to get it done. So if you\n \n\nuh just helps to get it done. So if you\nlook it up multineer I'm not trying to\n\nlook it up multineer I'm not trying to\n \n\nlook it up multineer I'm not trying to\nsell you anything. I'm not trying to\n\nsell you anything. I'm not trying to\n \n\nsell you anything. I'm not trying to\nlike vendor lock in or whatever. It's\n\nlike vendor lock in or whatever. It's\n \n\nlike vendor lock in or whatever. It's\ncompletely open source and if needed I\n\ncompletely open source and if needed I\n \n\ncompletely open source and if needed I\ncan just recreate it in a couple of days\n\ncan just recreate it in a couple of days\n \n\ncan just recreate it in a couple of days\nnow with cursor. The point is in the\n\nnow with cursor. The point is in the\n \n\nnow with cursor. The point is in the\napproach not in the platform. Uh so for\n\napproach not in the platform. Uh so for\n \n\napproach not in the platform. Uh so for\nexample here we see that very same\n\nexample here we see that very same\n \n\nexample here we see that very same\nquestion um how do I reset my password\n\nquestion um how do I reset my password\n \n\nquestion um how do I reset my password\nyou see the what was the input what was\n\nyou see the what was the input what was\n \n\nyou see the what was the input what was\nthe output and uh that specific criteria\n\nthe output and uh that specific criteria\n \n\nthe output and uh that specific criteria\nthat I measure it uh that specific\n\nthat I measure it uh that specific\n \n\nthat I measure it uh that specific\nquestion how do I know if the answer is\n\nquestion how do I know if the answer is\n \n\nquestion how do I know if the answer is\ncorrect and now I can just reiterate and\n\ncorrect and now I can just reiterate and\n \n\ncorrect and now I can just reiterate and\ngenerate like 50 different variations of\n\ngenerate like 50 different variations of\n \n\ngenerate like 50 different variations of\nthe same question and see if I still get\n\nthe same question and see if I still get\n \n\nthe same question and see if I still get\nthe right answer if the answer matches\n\nthe right answer if the answer matches\n \n\nthe right answer if the answer matches\nall the checklist that I have for that\n\nall the checklist that I have for that\n \n\nall the checklist that I have for that\nspecific answer. specific answer. specific answer. Um how the process usually works\n\nUm how the process usually works\n \n\nUm how the process usually works\num so contrary to like regular approach\n\num so contrary to like regular approach\n \n\num so contrary to like regular approach\nyou build your evals not at the end of\n\nyou build your evals not at the end of\n \n\nyou build your evals not at the end of\nthe process but in the very beginning of\n\nthe process but in the very beginning of\n \n\nthe process but in the very beginning of\nthe process. So you just build your\n\nthe process. So you just build your\n \n\nthe process. So you just build your\nfirst version of the PC. You define the\n\nfirst version of the PC. You define the\n \n\nfirst version of the PC. You define the\nfirst version of your tests evaluations. first version of your tests evaluations. first version of your tests evaluations. You run them and you see what's going\n\nYou run them and you see what's going\n \n\nYou run them and you see what's going\non. You you will see that uh in some\n\non. You you will see that uh in some\n \n\non. You you will see that uh in some\ncases it will fail. Uh in some cases it\n\ncases it will fail. Uh in some cases it\n \n\ncases it will fail. Uh in some cases it\nwill succeed. What's important is to to\n\nwill succeed. What's important is to to\n \n\nwill succeed. What's important is to to\nlook at the details not just see the\n\nlook at the details not just see the\n \n\nlook at the details not just see the\naverage numbers. The average numbers\n\naverage numbers. The average numbers\n \n\naverage numbers. The average numbers\nwon't tell you anything. Uh won't tell\n\nwon't tell you anything. Uh won't tell\n \n\nwon't tell you anything. Uh won't tell\nyou how to improve it. If you actually\n\nyou how to improve it. If you actually\n \n\nyou how to improve it. If you actually\nlook at the details of each evaluation,\n\nlook at the details of each evaluation,\n \n\nlook at the details of each evaluation,\nyou'll see exactly why it's failing. It\n\nyou'll see exactly why it's failing. It\n \n\nyou'll see exactly why it's failing. It\ncould be failing um because your test is\n\ncould be failing um because your test is\n \n\ncould be failing um because your test is\nnot defined correctly. It could be\n\nnot defined correctly. It could be\n \n\nnot defined correctly. It could be\nfailing because your uh solution is not\n\nfailing because your uh solution is not\n \n\nfailing because your uh solution is not\nworking as it should be. And like in\n\nworking as it should be. And like in\n \n\nworking as it should be. And like in\norder to do it, you may need to uh to do\n\norder to do it, you may need to uh to do\n \n\norder to do it, you may need to uh to do\na change in like you may change a model,\n\na change in like you may change a model,\n \n\na change in like you may change a model,\nyou may change something on in your\n\nyou may change something on in your\n \n\nyou may change something on in your\nlogic, you may change a prompt or the\n\nlogic, you may change a prompt or the\n \n\nlogic, you may change a prompt or the\ndata that you use in order to uh answer\n\ndata that you use in order to uh answer\n \n\ndata that you use in order to uh answer\na question in our example. a question in our example. a question in our example. And uh basically what you do now is\n\nAnd uh basically what you do now is\n \n\nAnd uh basically what you do now is\nexperimentation. So you you start\n\nexperimentation. So you you start\n \n\nexperimentation. So you you start\nrunning your experiment. You change\n\nrunning your experiment. You change\n \n\nrunning your experiment. You change\nsomething. you you need to define these\n\nsomething. you you need to define these\n \n\nsomething. you you need to define these\ntests in a way that will uh help you to\n\ntests in a way that will uh help you to\n \n\ntests in a way that will uh help you to\nmake an educated guess on uh what you\n\nmake an educated guess on uh what you\n \n\nmake an educated guess on uh what you\nneed to change in order to to do it. In\n\nneed to change in order to to do it. In\n \n\nneed to change in order to to do it."
}
] |
[
{
"role": "system",
"content": "You are an AI Engineer content creator. Write in the style of Swyx and the Latent Space podcast - technical but accessible, with practical insights about AI engineering, agents, LLMs, and developer tools. Be direct, insightful, and focus on what matters to practitioners."
},
{
"role": "user",
"content": "Share your insights on this AI engineering topic:\n\nIn\nsome cases it will work in some cases it\n\nsome cases it will work in some cases it\n \n\nsome cases it will work in some cases it\nwon't. But even if it works uh let's say\n\nwon't. But even if it works uh let's say\n \n\nwon't. But even if it works uh let's say\nyou change something in your prompt and\n\nyo..."
},
{
"role": "assistant",
"content": "In\nsome cases it will work in some cases it\n\nsome cases it will work in some cases it\n \n\nsome cases it will work in some cases it\nwon't. But even if it works uh let's say\n\nwon't. But even if it works uh let's say\n \n\nwon't. But even if it works uh let's say\nyou change something in your prompt and\n\nyou change something in your prompt and\n \n\nyou change something in your prompt and\nit fixed this test. In my experience, in\n\nit fixed this test. In my experience, in\n \n\nit fixed this test. In my experience, in\nmany cases, it breaks uh something that\n\nmany cases, it breaks uh something that\n \n\nmany cases, it breaks uh something that\nused to work before. Uh like you you you\n\nused to work before. Uh like you you you\n \n\nused to work before. Uh like you you you\nhave constant regressions and if you\n\nhave constant regressions and if you\n \n\nhave constant regressions and if you\ndon't have these evaluations, there is\n\ndon't have these evaluations, there is\n \n\ndon't have these evaluations, there is\nno way you'll be able to catch it on\n\nno way you'll be able to catch it on\n \n\nno way you'll be able to catch it on\ntime. time. time. So this is hugely important and what\n\nSo this is hugely important and what\n \n\nSo this is hugely important and what\nactually happens is that again you build\n\nactually happens is that again you build\n \n\nactually happens is that again you build\nyour first version. You build your first\n\nyour first version. You build your first\n \n\nyour first version. You build your first\nversion of the vows uh you match them\n\nversion of the vows uh you match them\n \n\nversion of the vows uh you match them\nyou run these valves you improve\n\nyou run these valves you improve\n \n\nyou run these valves you improve\nsomething you improve your vows or maybe\n\nsomething you improve your vows or maybe\n \n\nsomething you improve your vows or maybe\nadd more evaluations and then you like\n\nadd more evaluations and then you like\n \n\nadd more evaluations and then you like\ncontinuously improve it until you reach\n\ncontinuously improve it until you reach\n \n\ncontinuously improve it until you reach\nsome point where you are satisfied with\n\nsome point where you are satisfied with\n \n\nsome point where you are satisfied with\nyour valves for this specific solution\n\nyour valves for this specific solution\n \n\nyour valves for this specific solution\nfor that specific point of time. And\n\nfor that specific point of time. And\n \n\nfor that specific point of time. And\nwhat actually happened is that you you\n\nwhat actually happened is that you you\n \n\nwhat actually happened is that you you\nyou got your baseline, you got your\n\nyou got your baseline, you got your\n \n\nyou got your baseline, you got your\nbenchmark that uh now you can start\n\nbenchmark that uh now you can start\n \n\nbenchmark that uh now you can start\noptimizing and uh you have the\n\noptimizing and uh you have the\n \n\noptimizing and uh you have the\nconfidence that the tests should be\n\nconfidence that the tests should be\n \n\nconfidence that the tests should be\nworking. So now you can try another\n\nworking. So now you can try another\n \n\nworking. So now you can try another\nmodel. Let's say well what how can I try\n\nmodel. Let's say well what how can I try\n \n\nmodel. Let's say well what how can I try\nto see if 40 mini will work the same way\n\nto see if 40 mini will work the same way\n \n\nto see if 40 mini will work the same way\nwith 40 or not? uh can I use a graph rag\n\nwith 40 or not? uh can I use a graph rag\n \n\nwith 40 or not? uh can I use a graph rag\nor can I try a simpler solution? or can I try a simpler solution? or can I try a simpler solution? uh should I have uh to use agentic\n\nuh should I have uh to use agentic\n \n\nuh should I have uh to use agentic\napproach that like maybe better but uh\n\napproach that like maybe better but uh\n \n\napproach that like maybe better but uh\nrequires more time more uh inference\n\nrequires more time more uh inference\n \n\nrequires more time more uh inference\ncost etc or should I try to simplify the\n\ncost etc or should I try to simplify the\n \n\ncost etc or should I try to simplify the\nlogic or maybe I can simplify the logic\n\nlogic or maybe I can simplify the logic\n \n\nlogic or maybe I can simplify the logic\nfor a specific portion of the\n\nfor a specific portion of the\n \n\nfor a specific portion of the\napplication etc etc having this\n\napplication etc etc having this\n \n\napplication etc etc having this\nbenchmark uh allows you to do all these\n\nbenchmark uh allows you to do all these\n \n\nbenchmark uh allows you to do all these\nexperimentations uh with confidence but\n\nexperimentations uh with confidence but\n \n\nexperimentations uh with confidence but\nagain the the most important part is\n\nagain the the most important part is\n \n\nagain the the most important part is\nlike how do you reach this benchmark\n\nlike how do you reach this benchmark\n \n\nlike how do you reach this benchmark\nAnd uh while the approach is uh pretty\n\nAnd uh while the approach is uh pretty\n \n\nAnd uh while the approach is uh pretty\nmuch the same, the evaluations that you\n\nmuch the same, the evaluations that you\n \n\nmuch the same, the evaluations that you\nneed to build and how do you build your\n\nneed to build and how do you build your\n \n\nneed to build and how do you build your\nevaluations are completely different\n\nevaluations are completely different\n \n\nevaluations are completely different\ndepending on the solution that you need\n\ndepending on the solution that you need\n \n\ndepending on the solution that you need\nto build because uh the models are super\n\nto build because uh the models are super\n \n\nto build because uh the models are super\ncapable right now. Uh so they allow you\n\ncapable right now. Uh so they allow you\n \n\ncapable right now. Uh so they allow you\nto build a huge variety of uh solutions\n\nto build a huge variety of uh solutions\n \n\nto build a huge variety of uh solutions\nbut each and every solution is quite uh\n\nbut each and every solution is quite uh\n \n\nbut each and every solution is quite uh\ndifferent in terms of how do you uh\n\ndifferent in terms of how do you uh\n \n\ndifferent in terms of how do you uh\nevaluate it. uh for support bot you\n\nevaluate it. uh for support bot you\n \n\nevaluate it. uh for support bot you\nusually typically use LM as a judge as I\n\nusually typically use LM as a judge as I\n \n\nusually typically use LM as a judge as I\nuh made an example if you're building\n\nuh made an example if you're building\n \n\nuh made an example if you're building\ntext to SQL or text to graph database\n\ntext to SQL or text to graph database\n \n\ntext to SQL or text to graph database\nthen uh to my experience the best way is\n\nthen uh to my experience the best way is\n \n\nthen uh to my experience the best way is\nto create a mock database that\n\nto create a mock database that\n \n\nto create a mock database that\nrepresents the um whatever uh database\n\nrepresents the um whatever uh database\n \n\nrepresents the um whatever uh database\nor databases that you need your solution\n\nor databases that you need your solution\n \n\nor databases that you need your solution\nto work with they represent the same\n\nto work with they represent the same\n \n\nto work with they represent the same\nschema and you have a mock data so you\n\nschema and you have a mock data so you\n \n\nschema and you have a mock data so you\nknow exactly uh what should expect on\n\nknow exactly uh what should expect on\n \n\nknow exactly uh what should expect on\nspecific questions. Um if you need to\n\nspecific questions. Um if you need to\n \n\nspecific questions. Um if you need to\nbuild some classifier for call center\n\nbuild some classifier for call center\n \n\nbuild some classifier for call center\nconversations then your uh tests are\n\nconversations then your uh tests are\n \n\nconversations then your uh tests are\nlike simple match whenever this is this\n\nlike simple match whenever this is this\n \n\nlike simple match whenever this is this\nis the right rubric or not. Uh and the\n\nis the right rubric or not. Uh and the\n \n\nis the right rubric or not. Uh and the\nsame appro uh approach applies to guard\n\nsame appro uh approach applies to guard\n \n\nsame appro uh approach applies to guard\nrails."
}
] |
[
{
"role": "system",
"content": "You are an AI Engineer content creator. Write in the style of Swyx and the Latent Space podcast - technical but accessible, with practical insights about AI engineering, agents, LLMs, and developer tools. Be direct, insightful, and focus on what matters to practitioners."
},
{
"role": "user",
"content": "Share your insights on this AI engineering topic:\n\nSo uh getting back to the support\n\nrails. So uh getting back to the support\n \n\nrails. So uh getting back to the support\nto the uh example of the customer\n\nto the uh example of the customer\n \n\nto the uh example of the customer\nsupport bot uh guardrails you need to\n\nsupport bot uh guardrails you need ..."
},
{
"role": "assistant",
"content": "So uh getting back to the support\n\nrails. So uh getting back to the support\n \n\nrails. So uh getting back to the support\nto the uh example of the customer\n\nto the uh example of the customer\n \n\nto the uh example of the customer\nsupport bot uh guardrails you need to\n\nsupport bot uh guardrails you need to\n \n\nsupport bot uh guardrails you need to\ncover uh questions that should not be\n\ncover uh questions that should not be\n \n\ncover uh questions that should not be\nanswered or questions that should be\n\nanswered or questions that should be\n \n\nanswered or questions that should be\nanswered in different ways or questions\n\nanswered in different ways or questions\n \n\nanswered in different ways or questions\nthat uh uh the answers are not in the\n\nthat uh uh the answers are not in the\n \n\nthat uh uh the answers are not in the\nmaterial. So all of these you can put\n\nmaterial. So all of these you can put\n \n\nmaterial. So all of these you can put\ninto your benchmark just different type\n\ninto your benchmark just different type\n \n\ninto your benchmark just different type\nof benchmark but it's pretty much the\n\nof benchmark but it's pretty much the\n \n\nof benchmark but it's pretty much the\nsame approach. same approach. same approach. Uh so just to reiterate uh the key\n\nUh so just to reiterate uh the key\n \n\nUh so just to reiterate uh the key\ntakeaways, you need to evaluate your\n\ntakeaways, you need to evaluate your\n \n\ntakeaways, you need to evaluate your\napps the way your users actually use\n\napps the way your users actually use\n \n\napps the way your users actually use\nthem. Um and uh avoid abstract metrics\n\nthem. Um and uh avoid abstract metrics\n \n\nthem. Um and uh avoid abstract metrics\nuh because these abstract connectors\n\nuh because these abstract connectors\n \n\nuh because these abstract connectors\ndon't really measure anything important. don't really measure anything important. don't really measure anything important. Uh and the approach is uh through\n\nUh and the approach is uh through\n \n\nUh and the approach is uh through\nexperimentation. So you run these\n\nexperimentation. So you run these\n \n\nexperimentation. So you run these\nevaluations frequently. you that allows\n\nevaluations frequently. you that allows\n \n\nevaluations frequently. you that allows\nyou to have rapid progress with uh less\n\nyou to have rapid progress with uh less\n \n\nyou to have rapid progress with uh less\nregressions because testing frequently\n\nregressions because testing frequently\n \n\nregressions because testing frequently\nhelp you to to catch these surprises. Uh\n\nhelp you to to catch these surprises. Uh\n \n\nhelp you to to catch these surprises. Uh\nbut most importantly what you get if you\n\nbut most importantly what you get if you\n \n\nbut most importantly what you get if you\ndivi define your evaluations correctly,\n\ndivi define your evaluations correctly,\n \n\ndivi define your evaluations correctly,\nyou get your solution pretty much uh as\n\nyou get your solution pretty much uh as\n \n\nyou get your solution pretty much uh as\nkind of explainable AI because you know\n\nkind of explainable AI because you know\n \n\nkind of explainable AI because you know\nexactly what it does, you know exactly\n\nexactly what it does, you know exactly\n \n\nexactly what it does, you know exactly\nhow it does it if you test it the right\n\nhow it does it if you test it the right\n \n\nhow it does it if you test it the right\nway. way. way. Thank you very much. Uh take a look at\n\nThank you very much. Uh take a look at\n \n\nThank you very much. Uh take a look at\nmultineer uh that's a platform that you\n\nmultineer uh that's a platform that you\n \n\nmultineer uh that's a platform that you\ncan use to uh run these evaluations. You\n\ncan use to uh run these evaluations. You\n \n\ncan use to uh run these evaluations. You\ncan totally use any other platform. The\n\ncan totally use any other platform. The\n \n\ncan totally use any other platform. The\napproach is quite simple. It doesn't\n\napproach is quite simple. It doesn't\n \n\napproach is quite simple. It doesn't\nrequire any specific platform. Uh I've\n\nrequire any specific platform. Uh I've\n \n\nrequire any specific platform. Uh I've\nbuilt multin just because no other\n\nbuilt multin just because no other\n \n\nbuilt multin just because no other\nplatform helped me to do it this way to\n\nplatform helped me to do it this way to\n \n\nplatform helped me to do it this way to\nto help me with the process of\n\nto help me with the process of\n \n\nto help me with the process of\nevaluation like end to end. Um, I'm\n\nevaluation like end to end. Um, I'm\n \n\nevaluation like end to end. Um, I'm\nworking on a startup that does reliable\n\nworking on a startup that does reliable\n \n\nworking on a startup that does reliable\nAI automation right now. Um, and uh,\n\nAI automation right now. Um, and uh,\n \n\nAI automation right now. Um, and uh,\nyeah, thank you very much. yeah, thank you very much. yeah, thank you very much. [Music]"
}
] |
[
{
"role": "system",
"content": "You are an AI Engineer content creator. Write in the style of Swyx and the Latent Space podcast - technical but accessible, with practical insights about AI engineering, agents, LLMs, and developer tools. Be direct, insightful, and focus on what matters to practitioners."
},
{
"role": "user",
"content": "Share your insights on this AI engineering topic:\n\n[music]\n\n \n\nThanks everybody for uh for joining. I'm\n\nThanks everybody for uh for joining. I'm\n \n\nThanks everybody for uh for joining. I'm\nhere to talk to you today about DSPI. here to talk to you today about DSPI. here to talk to you today about DSPI. Um, and feel free to jump in with\n\nUm, and feel..."
},
{
"role": "assistant",
"content": "[music]\n\n \n\nThanks everybody for uh for joining. I'm\n\nThanks everybody for uh for joining. I'm\n \n\nThanks everybody for uh for joining. I'm\nhere to talk to you today about DSPI. here to talk to you today about DSPI. here to talk to you today about DSPI. Um, and feel free to jump in with\n\nUm, and feel free to jump in with\n \n\nUm, and feel free to jump in with\nquestions or anything throughout the\n\nquestions or anything throughout the\n \n\nquestions or anything throughout the\ntalk. It's, you know, I don't sp I don't\n\ntalk. It's, you know, I don't sp I don't\n \n\ntalk. It's, you know, I don't sp I don't\nplan on spending the full hour and a\n\nplan on spending the full hour and a\n \n\nplan on spending the full hour and a\nhalf or so. I know it's the last session\n\nhalf or so. I know it's the last session\n \n\nhalf or so. I know it's the last session\nof the day. So, um, keep it casual. Feel\n\nof the day. So, um, keep it casual. Feel\n \n\nof the day. So, um, keep it casual. Feel\nfree to jump in. I'll start with a\n\nfree to jump in. I'll start with a\n \n\nfree to jump in. I'll start with a\nlittle bit of background. Don't want to\n\nlittle bit of background. Don't want to\n \n\nlittle bit of background. Don't want to\ngo through too many slides. I'm\n\ngo through too many slides. I'm\n \n\ngo through too many slides. I'm\ntechnically a consultant, so I have to\n\ntechnically a consultant, so I have to\n \n\ntechnically a consultant, so I have to\ndo some slides, but we will dive into\n\ndo some slides, but we will dive into\n \n\ndo some slides, but we will dive into\nthe code for the the latter half. And\n\nthe code for the the latter half. And\n \n\nthe code for the the latter half. And\nthere's a GitHub repo that you can\n\nthere's a GitHub repo that you can\n \n\nthere's a GitHub repo that you can\ndownload to to follow along and play\n\ndownload to to follow along and play\n \n\ndownload to to follow along and play\naround with it on your own. around with it on your own. around with it on your own. Um, so how many people here have heard\n\nUm, so how many people here have heard\n \n\nUm, so how many people here have heard\nof DSPI? of DSPI? of DSPI? Almost everyone. That's awesome. How\n\nAlmost everyone. That's awesome. How\n \n\nAlmost everyone. That's awesome. How\nmany people have actually used it kind\n\nmany people have actually used it kind\n \n\nmany people have actually used it kind\nof day-to-day in production or anything\n\nof day-to-day in production or anything\n \n\nof day-to-day in production or anything\nlike that? Three. Okay, good. So\n\nlike that? Three. Okay, good. So\n \n\nlike that? Three. Okay, good. So\nhopefully we can convert some more of\n\nhopefully we can convert some more of\n \n\nhopefully we can convert some more of\nyou today. Um, so high level DSPI, this\n\nyou today. Um, so high level DSPI, this\n \n\nyou today. Um, so high level DSPI, this\nis straight from the website. Um, it's a\n\nis straight from the website. Um, it's a\n \n\nis straight from the website. Um, it's a\ndeclarative framework for how you can\n\ndeclarative framework for how you can\n \n\ndeclarative framework for how you can\nbuild modular software. And most\n\nbuild modular software. And most\n \n\nbuild modular software. And most\nimportant for someone like myself, I'm\n\nimportant for someone like myself, I'm\n \n\nimportant for someone like myself, I'm\nnot necessarily an engineer that is\n\nnot necessarily an engineer that is\n \n\nnot necessarily an engineer that is\nwriting code all day, every day. As I\n\nwriting code all day, every day. As I\n \n\nwriting code all day, every day. As I\nmentioned before, I'm a more of a\n\nmentioned before, I'm a more of a\n \n\nmentioned before, I'm a more of a\ntechnical consultant. So, I run across a\n\ntechnical consultant. So, I run across a\n \n\ntechnical consultant. So, I run across a\nvariety of different problems. Could be\n\nvariety of different problems. Could be\n \n\nvariety of different problems. Could be\num an investigation for a law firm. It\n\num an investigation for a law firm. It\n \n\num an investigation for a law firm. It\ncould be helping a company understand\n\ncould be helping a company understand\n \n\ncould be helping a company understand\nhow to improve their processes, how to\n\nhow to improve their processes, how to\n \n\nhow to improve their processes, how to\ndeploy AI internally. Maybe we need to\n\ndeploy AI internally. Maybe we need to\n \n\ndeploy AI internally. Maybe we need to\nlook through 10 10,000 contracts to\n\nlook through 10 10,000 contracts to\n \n\nlook through 10 10,000 contracts to\nidentify a particular clause um or or\n\nidentify a particular clause um or or\n \n\nidentify a particular clause um or or\nparagraph. And so DSPI has been a really\n\nparagraph. And so DSPI has been a really\n \n\nparagraph. And so DSPI has been a really\nnice way for me personally and my team\n\nnice way for me personally and my team\n \n\nnice way for me personally and my team\nto iterate really really quickly on\n\nto iterate really really quickly on\n \n\nto iterate really really quickly on\nbuilding these applications. building these applications. building these applications. Most importantly building programs. It's\n\nMost importantly building programs. It's\n \n\nMost importantly building programs. It's\nnot um it's not kind of iterating with\n\nnot um it's not kind of iterating with\n \n\nnot um it's not kind of iterating with\nprompts and tweaking things back and\n\nprompts and tweaking things back and\n \n\nprompts and tweaking things back and\nforth. It is building a a proper Python\n\nforth. It is building a a proper Python\n \n\nforth. It is building a a proper Python\nprogram and and DSP is a really good way\n\nprogram and and DSP is a really good way\n \n\nprogram and and DSP is a really good way\nfor you to do that. for you to do that. for you to do that. So I mentioned before there's a repo\n\nSo I mentioned before there's a repo\n \n\nSo I mentioned before there's a repo\nonline if you want to download it now\n\nonline if you want to download it now\n \n\nonline if you want to download it now\nand kind of just get everything set up. and kind of just get everything set up. and kind of just get everything set up. I'll put this on the screen later on. I'll put this on the screen later on. I'll put this on the screen later on. Um, but if you want to go here, just\n\nUm, but if you want to go here, just\n \n\nUm, but if you want to go here, just\nkind of download some of the code. It uh\n\nkind of download some of the code. It uh\n \n\nkind of download some of the code. It uh\nit's been put together over the past\n\nit's been put together over the past\n \n\nit's been put together over the past\ncouple days. So, it's not going to be\n\ncouple days. So, it's not going to be\n \n\ncouple days. So, it's not going to be\nperfect production level code. It's much\n\nperfect production level code. It's much\n \n\nperfect production level code. It's much\nmore of utilities and little things here\n\nmore of utilities and little things here\n \n\nmore of utilities and little things here\nand there to just come and kind of\n\nand there to just come and kind of\n \n\nand there to just come and kind of\ndemonstrate the usefulness, demonstrate\n\ndemonstrate the usefulness, demonstrate\n \n\ndemonstrate the usefulness, demonstrate\nthe point of of what we're talking about\n\nthe point of of what we're talking about\n \n\nthe point of of what we're talking about\ntoday in that and we'll walk through all\n\ntoday in that and we'll walk through all\n \n\ntoday in that and we'll walk through all\nof these these different use cases. So\n\nof these these different use cases. So\n \n\nof these these different use cases."
}
] |
[
{
"role": "system",
"content": "You are an AI Engineer content creator. Write in the style of Swyx and the Latent Space podcast - technical but accessible, with practical insights about AI engineering, agents, LLMs, and developer tools. Be direct, insightful, and focus on what matters to practitioners."
},
{
"role": "user",
"content": "Share your insights on this AI engineering topic:\n\nSo\num sentiment classifier going through a\n\num sentiment classifier going through a\n \n\num sentiment classifier going through a\nPDF some multimodal work uh a very very\n\nPDF some multimodal work uh a very very\n \n\nPDF some multimodal work uh a very very\nsimple web research agent detecting\n\nsimple web r..."
},
{
"role": "assistant",
"content": "So\num sentiment classifier going through a\n\num sentiment classifier going through a\n \n\num sentiment classifier going through a\nPDF some multimodal work uh a very very\n\nPDF some multimodal work uh a very very\n \n\nPDF some multimodal work uh a very very\nsimple web research agent detecting\n\nsimple web research agent detecting\n \n\nsimple web research agent detecting\nboundaries of a PDF document you'll see\n\nboundaries of a PDF document you'll see\n \n\nboundaries of a PDF document you'll see\nhow to summarize basically arbitrary\n\nhow to summarize basically arbitrary\n \n\nhow to summarize basically arbitrary\nlength text and then go into an\n\nlength text and then go into an\n \n\nlength text and then go into an\noptimizer uh with Jeepo\n\noptimizer uh with Jeepo\n \n\noptimizer uh with Jeepo\nbut before we do that just again kind of\n\nbut before we do that just again kind of\n \n\nbut before we do that just again kind of\nlevel set the biggest thing for me\n\nlevel set the biggest thing for me\n \n\nlevel set the biggest thing for me\npersonally DSP is a really nice way to\n\npersonally DSP is a really nice way to\n \n\npersonally DSP is a really nice way to\ndecompose your logic into a program that\n\ndecompose your logic into a program that\n \n\ndecompose your logic into a program that\ntreats LLMs as a first class citizen. So\n\ntreats LLMs as a first class citizen. So\n \n\ntreats LLMs as a first class citizen. So\nat the end of the day, you're\n\nat the end of the day, you're\n \n\nat the end of the day, you're\nfundamentally just calling a function\n\nfundamentally just calling a function\n \n\nfundamentally just calling a function\nthat under the hood just happens to be\n\nthat under the hood just happens to be\n \n\nthat under the hood just happens to be\nan LLM and DSPI gives you a really nice\n\nan LLM and DSPI gives you a really nice\n \n\nan LLM and DSPI gives you a really nice\nintuitive easy way to do that with some\n\nintuitive easy way to do that with some\n \n\nintuitive easy way to do that with some\nguarantees about the input and output\n\nguarantees about the input and output\n \n\nguarantees about the input and output\ntypes. So of course there are structured\n\ntypes. So of course there are structured\n \n\ntypes. So of course there are structured\noutputs, of course there are other ways\n\noutputs, of course there are other ways\n \n\noutputs, of course there are other ways\nto do this, Pyantic [snorts]\n\nto do this, Pyantic [snorts]\n \n\nto do this, Pyantic [snorts]\nand others. Um, but DSPI has a set of\n\nand others. Um, but DSPI has a set of\n \n\nand others. Um, but DSPI has a set of\nprimitives that when you put it all\n\nprimitives that when you put it all\n \n\nprimitives that when you put it all\ntogether allows you to build a cohesive\n\ntogether allows you to build a cohesive\n \n\ntogether allows you to build a cohesive\nmodular piece of software that you then\n\nmodular piece of software that you then\n \n\nmodular piece of software that you then\nhappen to be able to optimize. We'll get\n\nhappen to be able to optimize. We'll get\n \n\nhappen to be able to optimize. We'll get\ninto that uh in a minute. into that uh in a minute. into that uh in a minute. So, just a few reasons of why I'm such\n\nSo, just a few reasons of why I'm such\n \n\nSo, just a few reasons of why I'm such\nan advocate. It sit at it sits at this\n\nan advocate. It sit at it sits at this\n \n\nan advocate. It sit at it sits at this\nreally nice level of abstraction. So,\n\nreally nice level of abstraction. So,\n \n\nreally nice level of abstraction. So,\nit's I I would say it doesn't get in\n\nit's I I would say it doesn't get in\n \n\nit's I I would say it doesn't get in\nyour way as much as a lang chain. And\n\nyour way as much as a lang chain. And\n \n\nyour way as much as a lang chain. And\nthat's not a knock-on lang chain. It's\n\nthat's not a knock-on lang chain. It's\n \n\nthat's not a knock-on lang chain. It's\njust a different kind of paradigm in the\n\njust a different kind of paradigm in the\n \n\njust a different kind of paradigm in the\nway that DSPI is is structured. Um, and\n\nway that DSPI is is structured. Um, and\n \n\nway that DSPI is is structured. Um, and\nallows you to focus on things that\n\nallows you to focus on things that\n \n\nallows you to focus on things that\nactually matter. So you're not writing\n\nactually matter. So you're not writing\n \n\nactually matter. So you're not writing\nchoices zero messages content. You're\n\nchoices zero messages content. You're\n \n\nchoices zero messages content. You're\nnot you're not doing string parser. not you're not doing string parser. not you're not doing string parser. You're not doing a bunch of stuff under\n\nYou're not doing a bunch of stuff under\n \n\nYou're not doing a bunch of stuff under\nthe hood. You're just declaring your\n\nthe hood. You're just declaring your\n \n\nthe hood. You're just declaring your\nintent of how you want the program to\n\nintent of how you want the program to\n \n\nintent of how you want the program to\noperate, what you want your inputs and\n\noperate, what you want your inputs and\n \n\noperate, what you want your inputs and\noutputs to be. outputs to be. outputs to be. Because of this, it allows you to create\n\nBecause of this, it allows you to create\n \n\nBecause of this, it allows you to create\ncomputer programs. As I mentioned\n\ncomputer programs. As I mentioned\n \n\ncomputer programs. As I mentioned\nbefore, not just tweaking strings and\n\nbefore, not just tweaking strings and\n \n\nbefore, not just tweaking strings and\nsending them back and forth. You are\n\nsending them back and forth. You are\n \n\nsending them back and forth. You are\nbuilding a program first. It just\n\nbuilding a program first. It just\n \n\nbuilding a program first. It just\nhappens to also use LLMs. And really the\n\nhappens to also use LLMs. And really the\n \n\nhappens to also use LLMs. And really the\nthe most kind of important part of this\n\nthe most kind of important part of this\n \n\nthe most kind of important part of this\nis that and Omar the KB the uh the\n\nis that and Omar the KB the uh the\n \n\nis that and Omar the KB the uh the\nfounder of this or the the original\n\nfounder of this or the the original\n \n\nfounder of this or the the original\ndeveloper of it had this really good\n\ndeveloper of it had this really good\n \n\ndeveloper of it had this really good\npodcast with A16Z. I think it came out\n\npodcast with A16Z. I think it came out\n \n\npodcast with A16Z. I think it came out\njust like two or three days ago. But it\n\njust like two or three days ago. But it\n \n\njust like two or three days ago. But it\nhe put it a really nice way. He said\n\nhe put it a really nice way. He said\n \n\nhe put it a really nice way. He said\nit's a it's built with a systems mindset\n\nit's a it's built with a systems mindset\n \n\nit's a it's built with a systems mindset\nand it's really about how you're\n\nand it's really about how you're\n \n\nand it's really about how you're\nencoding or expressing your intent of\n\nencoding or expressing your intent of\n \n\nencoding or expressing your intent of\nwhat you want to do most importantly in\n\nwhat you want to do most importantly in\n \n\nwhat you want to do most importantly in\na way that's transferable. So the the\n\na way that's transferable. So the the\n \n\na way that's transferable. So the the\ndesign of your system, I would imagine,\n\ndesign of your system, I would imagine,\n \n\ndesign of your system, I would imagine,\nor your program isn't going to move\n\nor your program isn't going to move\n \n\nor your program isn't going to move\nnecessarily as quickly as maybe the\n\nnecessarily as quickly as maybe the\n \n\nnecessarily as quickly as maybe the\nmodel capabilities are under the hood. model capabilities are under the hood. model capabilities are under the hood."
}
] |
[
{
"role": "system",
"content": "You are an AI Engineer content creator. Write in the style of Swyx and the Latent Space podcast - technical but accessible, with practical insights about AI engineering, agents, LLMs, and developer tools. Be direct, insightful, and focus on what matters to practitioners."
},
{
"role": "user",
"content": "Share your insights on this AI engineering topic:\n\nwhen we see new releases almost every\n\nwhen we see new releases almost every\n \n\nwhen we see new releases almost every\nsingle day, different capabilities,\n\nsingle day, different capabilities,\n \n\nsingle day, different capabilities,\nbetter models and so DSPI allows you to\n\nbetter models and so DSPI all..."
},
{
"role": "assistant",
"content": "when we see new releases almost every\n\nwhen we see new releases almost every\n \n\nwhen we see new releases almost every\nsingle day, different capabilities,\n\nsingle day, different capabilities,\n \n\nsingle day, different capabilities,\nbetter models and so DSPI allows you to\n\nbetter models and so DSPI allows you to\n \n\nbetter models and so DSPI allows you to\nstructure it in a way that retains the\n\nstructure it in a way that retains the\n \n\nstructure it in a way that retains the\ncontrol flow uh retains the intent of\n\ncontrol flow uh retains the intent of\n \n\ncontrol flow uh retains the intent of\nyour system, your program um while\n\nyour system, your program um while\n \n\nyour system, your program um while\nallowing you to bounce from model to\n\nallowing you to bounce from model to\n \n\nallowing you to bounce from model to\nmodel to the extent that you want to or\n\nmodel to the extent that you want to or\n \n\nmodel to the extent that you want to or\nneed to. need to. need to. Convenience comes for free. There's no\n\nConvenience comes for free. There's no\n \n\nConvenience comes for free. There's no\nparsing, JSON, things like that. It\n\nparsing, JSON, things like that. It\n \n\nparsing, JSON, things like that. It\nagain, it sits at a nice level of\n\nagain, it sits at a nice level of\n \n\nagain, it sits at a nice level of\nabstraction where you can still\n\nabstraction where you can still\n \n\nabstraction where you can still\nunderstand what's going on under the\n\nunderstand what's going on under the\n \n\nunderstand what's going on under the\nhood. If you want to, you can go in and\n\nhood. If you want to, you can go in and\n \n\nhood. If you want to, you can go in and\ntweak things, but it allows you to to\n\ntweak things, but it allows you to to\n \n\ntweak things, but it allows you to to\nkind of focus on just what you want to\n\nkind of focus on just what you want to\n \n\nkind of focus on just what you want to\ndo while retaining the level of\n\ndo while retaining the level of\n \n\ndo while retaining the level of\nprecision that you that I think most of\n\nprecision that you that I think most of\n \n\nprecision that you that I think most of\nus would like to have in and kind of\n\nus would like to have in and kind of\n \n\nus would like to have in and kind of\nbuilding your programs. Um, [snorts]\n\nbuilding your programs. Um, [snorts]\n \n\nbuilding your programs. Um, [snorts]\nas mentioned, it's robust to kind of\n\nas mentioned, it's robust to kind of\n \n\nas mentioned, it's robust to kind of\nmodel and paradigm shifts. So, you can\n\nmodel and paradigm shifts. So, you can\n \n\nmodel and paradigm shifts. So, you can\nagain keep the logic of your program. Um\n\nagain keep the logic of your program. Um\n \n\nagain keep the logic of your program. Um\nbut it but keep that those LLMs infused\n\nbut it but keep that those LLMs infused\n \n\nbut it but keep that those LLMs infused\nin uh basically in line. Now that being\n\nin uh basically in line. Now that being\n \n\nin uh basically in line. Now that being\nsaid, you know, there are absolutely\n\nsaid, you know, there are absolutely\n \n\nsaid, you know, there are absolutely\nother great libraries out there. other great libraries out there. other great libraries out there. Pedantic AI, Langchain, there's many\n\nPedantic AI, Langchain, there's many\n \n\nPedantic AI, Langchain, there's many\nmany others that allow you to do similar\n\nmany others that allow you to do similar\n \n\nmany others that allow you to do similar\nthings. Agno is another one. Um this is\n\nthings. Agno is another one. Um this is\n \n\nthings. Agno is another one. Um this is\njust one perspective and um it may not\n\njust one perspective and um it may not\n \n\njust one perspective and um it may not\nbe perfect for your use case. For me, it\n\nbe perfect for your use case. For me, it\n \n\nbe perfect for your use case. For me, it\ntook me a little bit to kind of gro how\n\ntook me a little bit to kind of gro how\n \n\ntook me a little bit to kind of gro how\nDSPI works and you'll see why that is in\n\nDSPI works and you'll see why that is in\n \n\nDSPI works and you'll see why that is in\na minute. Um, so I would just recommend\n\na minute. Um, so I would just recommend\n \n\na minute. Um, so I would just recommend\nkind of have an have an open mind, play\n\nkind of have an have an open mind, play\n \n\nkind of have an have an open mind, play\nwith it. Um, run the code, tweak the\n\nwith it. Um, run the code, tweak the\n \n\nwith it. Um, run the code, tweak the\ncode, do whatever you need to do. Um,\n\ncode, do whatever you need to do. Um,\n \n\ncode, do whatever you need to do. Um,\nand just see how it might work, might\n\nand just see how it might work, might\n \n\nand just see how it might work, might\nwork for you. And really, this talk is\n\nwork for you. And really, this talk is\n \n\nwork for you. And really, this talk is\nmore about ways that I found it useful. more about ways that I found it useful. more about ways that I found it useful. It's not a dissertation on the ins and\n\nIt's not a dissertation on the ins and\n \n\nIt's not a dissertation on the ins and\nouts of every nook and cranny of DSPI. outs of every nook and cranny of DSPI. outs of every nook and cranny of DSPI. It's more of, you know, I've run into\n\nIt's more of, you know, I've run into\n \n\nIt's more of, you know, I've run into\nthese problems myself now. I naturally\n\nthese problems myself now. I naturally\n \n\nthese problems myself now. I naturally\nrun to DSPI to solve them. And this is\n\nrun to DSPI to solve them. And this is\n \n\nrun to DSPI to solve them. And this is\nkind of why. And the hope is that you\n\nkind of why. And the hope is that you\n \n\nkind of why. And the hope is that you\ncan extrapolate some of this to your own\n\ncan extrapolate some of this to your own\n \n\ncan extrapolate some of this to your own\nuse cases. So we we'll go through\n\nuse cases. So we we'll go through\n \n\nuse cases. So we we'll go through\neverything uh fairly quickly here, but\n\neverything uh fairly quickly here, but\n \n\neverything uh fairly quickly here, but\nthe core concepts of DSPI really comes\n\nthe core concepts of DSPI really comes\n \n\nthe core concepts of DSPI really comes\ndown to arguably five or these six that\n\ndown to arguably five or these six that\n \n\ndown to arguably five or these six that\nyou see on the screen here. So we'll go\n\nyou see on the screen here. So we'll go\n \n\nyou see on the screen here. So we'll go\ninto each of these in more detail, but\n\ninto each of these in more detail, but\n \n\ninto each of these in more detail, but\nhigh level signatures\n\nhigh level signatures\n \n\nhigh level signatures\nspecify what you want the L what\n\nspecify what you want the L what\n \n\nspecify what you want the L what\nbasically what you want your function\n\nbasically what you want your function\n \n\nbasically what you want your function\ncall to do. This is when you specify\n\ncall to do. This is when you specify\n \n\ncall to do. This is when you specify\nyour inputs, your outputs. Inputs and\n\nyour inputs, your outputs. Inputs and\n \n\nyour inputs, your outputs. Inputs and\noutputs can both be typed. Um, and you\n\noutputs can both be typed. Um, and you\n \n\noutputs can both be typed. Um, and you\ndefer the rest of the basically the how\n\ndefer the rest of the basically the how\n \n\ndefer the rest of the basically the how\nthe implementation of it to the LLM. And\n\nthe implementation of it to the LLM. And\n \n\nthe implementation of it to the LLM. And\nwe'll see how we how that all kind of\n\nwe'll see how we how that all kind of\n \n\nwe'll see how we how that all kind of\ncomes together uh in a minute. Modules\n\ncomes together uh in a minute. Modules\n \n\ncomes together uh in a minute. Modules\nthemselves are ways to logically\n\nthemselves are ways to logically\n \n\nthemselves are ways to logically\nstructure your program. They're based\n\nstructure your program. They're based\n \n\nstructure your program. They're based\noff of signatures. So, a module can have\n\noff of signatures. So, a module can have\n \n\noff of signatures."
}
] |
[
{
"role": "system",
"content": "You are an AI Engineer content creator. Write in the style of Swyx and the Latent Space podcast - technical but accessible, with practical insights about AI engineering, agents, LLMs, and developer tools. Be direct, insightful, and focus on what matters to practitioners."
},
{
"role": "user",
"content": "Share your insights on this AI engineering topic:\n\nSo, a module can have\none or more signatures embedded within\n\none or more signatures embedded within\n \n\none or more signatures embedded within\nit in addition to uh additional logic. it in addition to uh additional logic. it in addition to uh additional logic. and it's based off of um pietorrch and\n\n..."
},
{
"role": "assistant",
"content": "So, a module can have\none or more signatures embedded within\n\none or more signatures embedded within\n \n\none or more signatures embedded within\nit in addition to uh additional logic. it in addition to uh additional logic. it in addition to uh additional logic. and it's based off of um pietorrch and\n\nand it's based off of um pietorrch and\n \n\nand it's based off of um pietorrch and\nsome of the in terms of like the\n\nsome of the in terms of like the\n \n\nsome of the in terms of like the\nmethodology for how it's structured and\n\nmethodology for how it's structured and\n \n\nmethodology for how it's structured and\nyou'll you'll see how that uh comes to\n\nyou'll you'll see how that uh comes to\n \n\nyou'll you'll see how that uh comes to\nbe in a minute. Tools we're all familiar\n\nbe in a minute. Tools we're all familiar\n \n\nbe in a minute. Tools we're all familiar\nwith tools MCP and others and really\n\nwith tools MCP and others and really\n \n\nwith tools MCP and others and really\ntools fundamentally as DSPI looks at\n\ntools fundamentally as DSPI looks at\n \n\ntools fundamentally as DSPI looks at\nthem are just Python functions. So it's\n\nthem are just Python functions. So it's\n \n\nthem are just Python functions. So it's\njust a way for you to very easily expose\n\njust a way for you to very easily expose\n \n\njust a way for you to very easily expose\nPython functions to the LLM within the\n\nPython functions to the LLM within the\n \n\nPython functions to the LLM within the\nDSP kind of ecosystem if you will. um\n\nDSP kind of ecosystem if you will. um\n \n\nDSP kind of ecosystem if you will. um\nadapters\n\nadapters\n \n\nadapters\nlive in between your signature and the\n\nlive in between your signature and the\n \n\nlive in between your signature and the\nLLM call itself. I mean, as we all know,\n\nLLM call itself. I mean, as we all know,\n \n\nLLM call itself. I mean, as we all know,\nprompts are ultimately just strings of\n\nprompts are ultimately just strings of\n \n\nprompts are ultimately just strings of\ntext that are sent to the LLM. text that are sent to the LLM. text that are sent to the LLM. Signatures are a way for you to express\n\nSignatures are a way for you to express\n \n\nSignatures are a way for you to express\nyour intent at a at a higher level. And\n\nyour intent at a at a higher level. And\n \n\nyour intent at a at a higher level. And\nso, adapters are the things that sit in\n\nso, adapters are the things that sit in\n \n\nso, adapters are the things that sit in\nbetween those two. So, it's how you\n\nbetween those two. So, it's how you\n \n\nbetween those two. So, it's how you\ntranslate your inputs and outputs into a\n\ntranslate your inputs and outputs into a\n \n\ntranslate your inputs and outputs into a\nformat basically explodes out from your\n\nformat basically explodes out from your\n \n\nformat basically explodes out from your\ninitial signature into a format that is\n\ninitial signature into a format that is\n \n\ninitial signature into a format that is\nultimately the prompt that is sent to\n\nultimately the prompt that is sent to\n \n\nultimately the prompt that is sent to\nthe LLM. And so, you know, there's some\n\nthe LLM. And so, you know, there's some\n \n\nthe LLM. And so, you know, there's some\ndebate or some research on if certain\n\ndebate or some research on if certain\n \n\ndebate or some research on if certain\nmodels perform better with XML as an\n\nmodels perform better with XML as an\n \n\nmodels perform better with XML as an\nexample or BAML or JSON or others. And\n\nexample or BAML or JSON or others. And\n \n\nexample or BAML or JSON or others. And\nso adapters give you a nice easy\n\nso adapters give you a nice easy\n \n\nso adapters give you a nice easy\nabstraction to to basically mix and\n\nabstraction to to basically mix and\n \n\nabstraction to to basically mix and\nmatch those at at will as you want. match those at at will as you want. match those at at will as you want. Optimizers um are\n\nOptimizers um are\n \n\nOptimizers um are\nthe most interesting and for whatever\n\nthe most interesting and for whatever\n \n\nthe most interesting and for whatever\nreason the most controversial part of\n\nreason the most controversial part of\n \n\nreason the most controversial part of\nDSP. That's kind of the first thing that\n\nDSP. That's kind of the first thing that\n \n\nDSP. That's kind of the first thing that\npeople think of or at least when they\n\npeople think of or at least when they\n \n\npeople think of or at least when they\nhear of DSP they think optimizers. We'll\n\nhear of DSP they think optimizers. We'll\n \n\nhear of DSP they think optimizers. We'll\nsee a quote in a minute. It's not\n\nsee a quote in a minute. It's not\n \n\nsee a quote in a minute. It's not\noptimizers first. It is just a nice\n\noptimizers first. It is just a nice\n \n\noptimizers first. It is just a nice\nadded benefit and a nice capability that\n\nadded benefit and a nice capability that\n \n\nadded benefit and a nice capability that\nDSPI offers in addition to the ability\n\nDSPI offers in addition to the ability\n \n\nDSPI offers in addition to the ability\nto structure your program with the\n\nto structure your program with the\n \n\nto structure your program with the\nsignatures and modules and everything\n\nsignatures and modules and everything\n \n\nsignatures and modules and everything\nelse. Um, and metrics are used in tandem\n\nelse. Um, and metrics are used in tandem\n \n\nelse. Um, and metrics are used in tandem\nwith optimizers that that basically\n\nwith optimizers that that basically\n \n\nwith optimizers that that basically\ndefines how you measure success in your\n\ndefines how you measure success in your\n \n\ndefines how you measure success in your\nin uh your DSPI program. So the\n\nin uh your DSPI program. So the\n \n\nin uh your DSPI program. So the\noptimizers use the metrics to determine\n\noptimizers use the metrics to determine\n \n\noptimizers use the metrics to determine\nif it's finding the right path if you\n\nif it's finding the right path if you\n \n\nif it's finding the right path if you\nwill. will. will. So signature as I mentioned before it's\n\nSo signature as I mentioned before it's\n \n\nSo signature as I mentioned before it's\nhow you express your intent your\n\nhow you express your intent your\n \n\nhow you express your intent your\ndeclarative intent can be super simple\n\ndeclarative intent can be super simple\n \n\ndeclarative intent can be super simple\nstrings and this is the weirdest part\n\nstrings and this is the weirdest part\n \n\nstrings and this is the weirdest part\nfor me initially but is one of the most\n\nfor me initially but is one of the most\n \n\nfor me initially but is one of the most\npowerful parts uh of it now or it can be\n\npowerful parts uh of it now or it can be\n \n\npowerful parts uh of it now or it can be\nmore complicated class-based classbased\n\nmore complicated class-based classbased\n \n\nmore complicated class-based classbased\nobjects if you've used pyantic it that's\n\nobjects if you've used pyantic it that's\n \n\nobjects if you've used pyantic it that's\nbasically what what it runs on under the\n\nbasically what what it runs on under the\n \n\nbasically what what it runs on under the\nhood. hood. hood. So this is an example of one of the\n\nSo this is an example of one of the\n \n\nSo this is an example of one of the\nclass-based signatures. Again, it it's\n\nclass-based signatures. Again, it it's\n \n\nclass-based signatures. Again, it it's\nbasically just a pyantic object. basically just a pyantic object. basically just a pyantic object. What's super interesting about this is\n\nWhat's super interesting about this is\n \n\nWhat's super interesting about this is\nthat\n\nthat\n \n\nthat\nthe\n\nthe\n \n\nthe\nthe names of the fields themselves act\n\nthe names of the fields themselves act\n \n\nthe names of the fields themselves act\nalmost as like mini prompts. It's part\n\nalmost as like mini prompts. It's part\n \n\nalmost as like mini prompts. It's part\nof the prompt itself. And you'll see how\n\nof the prompt itself. And you'll see how\n \n\nof the prompt itself. And you'll see how\nthis comes to life in a minute. But\n\nthis comes to life in a minute. But\n \n\nthis comes to life in a minute."
}
] |
[
{
"role": "system",
"content": "You are an AI Engineer content creator. Write in the style of Swyx and the Latent Space podcast - technical but accessible, with practical insights about AI engineering, agents, LLMs, and developer tools. Be direct, insightful, and focus on what matters to practitioners."
},
{
"role": "user",
"content": "Share your insights on this AI engineering topic:\n\nBut\nwhat's ultimately passed to the model\n\nwhat's ultimately passed to the model\n \n\nwhat's ultimately passed to the model\nfrom something like this is it will say\n\nfrom something like this is it will say\n \n\nfrom something like this is it will say\nokay your inputs are going to be a\n\nokay your inputs a..."
},
{
"role": "assistant",
"content": "But\nwhat's ultimately passed to the model\n\nwhat's ultimately passed to the model\n \n\nwhat's ultimately passed to the model\nfrom something like this is it will say\n\nfrom something like this is it will say\n \n\nfrom something like this is it will say\nokay your inputs are going to be a\n\nokay your inputs are going to be a\n \n\nokay your inputs are going to be a\nparameter called text and it's based off\n\nparameter called text and it's based off\n \n\nparameter called text and it's based off\nof the name of the that particular\n\nof the name of the that particular\n \n\nof the name of the that particular\nparameter in this class. And so these\n\nparameter in this class. And so these\n \n\nparameter in this class. And so these\nthings are actually passed through. And\n\nthings are actually passed through. And\n \n\nthings are actually passed through. And\nso it's it's very important uh to be\n\nso it's it's very important uh to be\n \n\nso it's it's very important uh to be\nable to name your parameters in a way\n\nable to name your parameters in a way\n \n\nable to name your parameters in a way\nthat is intuitive for the model to be\n\nthat is intuitive for the model to be\n \n\nthat is intuitive for the model to be\nable to pick it up. Um, and you can add\n\nable to pick it up. Um, and you can add\n \n\nable to pick it up. Um, and you can add\nsome additional context or what have you\n\nsome additional context or what have you\n \n\nsome additional context or what have you\nin the description field here. So most\n\nin the description field here. So most\n \n\nin the description field here. So most\nof this, if not all of this, yes, it is\n\nof this, if not all of this, yes, it is\n \n\nof this, if not all of this, yes, it is\nproper, you know, typed Python code, but\n\nproper, you know, typed Python code, but\n \n\nproper, you know, typed Python code, but\nit's also it also serves almost as a\n\nit's also it also serves almost as a\n \n\nit's also it also serves almost as a\nprompt ultimately that feeds into the\n\nprompt ultimately that feeds into the\n \n\nprompt ultimately that feeds into the\nmodel. Um, and that's basically\n\nmodel. Um, and that's basically\n \n\nmodel. Um, and that's basically\ntranslated through the use of adapters. translated through the use of adapters. translated through the use of adapters. Um, and so just to highlight here like\n\nUm, and so just to highlight here like\n \n\nUm, and so just to highlight here like\nthese, it's the ones that are a little\n\nthese, it's the ones that are a little\n \n\nthese, it's the ones that are a little\nbit darker and bold, you know, those are\n\nbit darker and bold, you know, those are\n \n\nbit darker and bold, you know, those are\nthe things that are effectively part of\n\nthe things that are effectively part of\n \n\nthe things that are effectively part of\nthe prompt. uh that's been sent in and\n\nthe prompt. uh that's been sent in and\n \n\nthe prompt. uh that's been sent in and\nyou'll see kind of how DSPI works with\n\nyou'll see kind of how DSPI works with\n \n\nyou'll see kind of how DSPI works with\nall this and formats it in a way that\n\nall this and formats it in a way that\n \n\nall this and formats it in a way that\nagain allow you to just worry about what\n\nagain allow you to just worry about what\n \n\nagain allow you to just worry about what\nyou want. Worry about constructing your\n\nyou want. Worry about constructing your\n \n\nyou want. Worry about constructing your\nsignature instead of figuring out how\n\nsignature instead of figuring out how\n \n\nsignature instead of figuring out how\nbest to word something in the prompt. Go\n\nbest to word something in the prompt. Go\n \n\nbest to word something in the prompt. Go\n>> ahead. I have a really good prompt. I have a really good prompt. I have a really good prompt. >> Sure. Then I don't want this thing. >> That's exactly right. >> Sure. >> Sure. >> Sure. >> So the the question for folks online is\n\n>> So the the question for folks online is\n \n\n>> So the the question for folks online is\nwhat if I already have a great prompt? what if I already have a great prompt? what if I already have a great prompt? I've done all this work. I'm a I'm a\n\nI've done all this work. I'm a I'm a\n \n\nI've done all this work. I'm a I'm a\namazing prompt engineer. I don't want my\n\namazing prompt engineer. I don't want my\n \n\namazing prompt engineer. I don't want my\njob to go away or whatever. Um, yes. So,\n\njob to go away or whatever. Um, yes. So,\n \n\njob to go away or whatever. Um, yes. So,\nyou can absolutely start with a custom\n\nyou can absolutely start with a custom\n \n\nyou can absolutely start with a custom\nprompt or something that you have\n\nprompt or something that you have\n \n\nprompt or something that you have\ndemonstrated works really well. And\n\ndemonstrated works really well. And\n \n\ndemonstrated works really well. And\nyou're exactly right that's that can be\n\nyou're exactly right that's that can be\n \n\nyou're exactly right that's that can be\ndone in the dock string itself. There's\n\ndone in the dock string itself. There's\n \n\ndone in the dock string itself. There's\nthere's some other methods in order uh\n\nthere's some other methods in order uh\n \n\nthere's some other methods in order uh\nfor you to inject basically system\n\nfor you to inject basically system\n \n\nfor you to inject basically system\ninstructions or add additional things at\n\ninstructions or add additional things at\n \n\ninstructions or add additional things at\ncertain parts of the ultimate prompt and\n\ncertain parts of the ultimate prompt and\n \n\ncertain parts of the ultimate prompt and\nor of course you can just inject it in\n\nor of course you can just inject it in\n \n\nor of course you can just inject it in\nthe in the final string anyway. I mean\n\nthe in the final string anyway. I mean\n \n\nthe in the final string anyway. I mean\nit's just you know a string that is\n\nit's just you know a string that is\n \n\nit's just you know a string that is\nconstructed by VSPI. So um absolutely\n\nconstructed by VSPI. So um absolutely\n \n\nconstructed by VSPI. So um absolutely\nthis doesn't necessarily prevent you it\n\nthis doesn't necessarily prevent you it\n \n\nthis doesn't necessarily prevent you it\ndoes does not prevent you from adding in\n\ndoes does not prevent you from adding in\n \n\ndoes does not prevent you from adding in\nsome super prompt that you already have. some super prompt that you already have. some super prompt that you already have. Absolutely. Um and to your point it is\n\nAbsolutely. Um and to your point it is\n \n\nAbsolutely. Um and to your point it is\nit can serve as a nice starting point\n\nit can serve as a nice starting point\n \n\nit can serve as a nice starting point\nfrom which to build the rest of the\n\nfrom which to build the rest of the\n \n\nfrom which to build the rest of the\nsystem. system. system. Here's a shorthand version of the same\n\nHere's a shorthand version of the same\n \n\nHere's a shorthand version of the same\nexact thing which to me the first time I\n\nexact thing which to me the first time I\n \n\nexact thing which to me the first time I\nsaw this so this was like baffling to\n\nsaw this so this was like baffling to\n \n\nsaw this so this was like baffling to\nme. Um, but it it that's exactly how it\n\nme. Um, but it it that's exactly how it\n \n\nme. Um, but it it that's exactly how it\nworks is that you're basically again\n\nworks is that you're basically again\n \n\nworks is that you're basically again\nkind of deferring the implementation or\n\nkind of deferring the implementation or\n \n\nkind of deferring the implementation or\nthe logic or what have you to DSPI and\n\nthe logic or what have you to DSPI and\n \n\nthe logic or what have you to DSPI and\nthe model to basically figure out what\n\nthe model to basically figure out what\n \n\nthe model to basically figure out what\nyou want to do. So in this case, if I\n\nyou want to do. So in this case, if I\n \n\nyou want to do. So in this case, if I\nwant a super super simple text uh\n\nwant a super super simple text uh\n \n\nwant a super super simple text uh\nsentiment classifier, this is basically\n\nsentiment classifier, this is basically\n \n\nsentiment classifier, this is basically\nall you need. You're just saying, okay,\n\nall you need."
}
] |
[
{
"role": "system",
"content": "You are an AI Engineer content creator. Write in the style of Swyx and the Latent Space podcast - technical but accessible, with practical insights about AI engineering, agents, LLMs, and developer tools. Be direct, insightful, and focus on what matters to practitioners."
},
{
"role": "user",
"content": "Share your insights on this AI engineering topic:\n\nYou're just saying, okay,\n \n\nall you need. You're just saying, okay,\nI'm going to give you text as an input. I'm going to give you text as an input. I'm going to give you text as an input. I want the sentiment as an integer as\n\nI want the sentiment as an integer as\n \n\nI want the sentiment as an inte..."
},
{
"role": "assistant",
"content": "You're just saying, okay,\n \n\nall you need. You're just saying, okay,\nI'm going to give you text as an input. I'm going to give you text as an input. I'm going to give you text as an input. I want the sentiment as an integer as\n\nI want the sentiment as an integer as\n \n\nI want the sentiment as an integer as\nthe output. Now you probably want to\n\nthe output. Now you probably want to\n \n\nthe output. Now you probably want to\nspecify some additional instructions to\n\nspecify some additional instructions to\n \n\nspecify some additional instructions to\nsay okay your sentiment you know a lower\n\nsay okay your sentiment you know a lower\n \n\nsay okay your sentiment you know a lower\nnumber means negative you know a higher\n\nnumber means negative you know a higher\n \n\nnumber means negative you know a higher\nnumber is more positive sentiment etc. number is more positive sentiment etc. number is more positive sentiment etc. But it just gives you a nice kind of\n\nBut it just gives you a nice kind of\n \n\nBut it just gives you a nice kind of\neasy way to to kind of scaffold these\n\neasy way to to kind of scaffold these\n \n\neasy way to to kind of scaffold these\nthings out in a way that you don't have\n\nthings out in a way that you don't have\n \n\nthings out in a way that you don't have\nto worry about like you know creating\n\nto worry about like you know creating\n \n\nto worry about like you know creating\nthis whole prompt from hand. It's like\n\nthis whole prompt from hand. It's like\n \n\nthis whole prompt from hand. It's like\nokay I just want to see how this works\n\nokay I just want to see how this works\n \n\nokay I just want to see how this works\nand then if it works then I can add the\n\nand then if it works then I can add the\n \n\nand then if it works then I can add the\nadditional instructions then I can\n\nadditional instructions then I can\n \n\nadditional instructions then I can\ncreate a module out of it or you know\n\ncreate a module out of it or you know\n \n\ncreate a module out of it or you know\nwhatever it might be. It's these\n\nwhatever it might be. It's these\n \n\nwhatever it might be. It's these\nshorthand\n\nshorthand\n \n\nshorthand\nor it is this shorthand that makes\n\nor it is this shorthand that makes\n \n\nor it is this shorthand that makes\nexperimentation and iteration incredibly\n\nexperimentation and iteration incredibly\n \n\nexperimentation and iteration incredibly\nquick. quick. quick. So modules it's that base abstraction\n\nSo modules it's that base abstraction\n \n\nSo modules it's that base abstraction\nlayer for DSPI programs. There are a\n\nlayer for DSPI programs. There are a\n \n\nlayer for DSPI programs. There are a\nbunch of modules that are built in and\n\nbunch of modules that are built in and\n \n\nbunch of modules that are built in and\nthese are a collection of kind of\n\nthese are a collection of kind of\n \n\nthese are a collection of kind of\nprompting techniques if you will and you\n\nprompting techniques if you will and you\n \n\nprompting techniques if you will and you\ncan always create your own module. So to\n\ncan always create your own module. So to\n \n\ncan always create your own module. So to\nthe question before, if you have\n\nthe question before, if you have\n \n\nthe question before, if you have\nsomething that you know works really\n\nsomething that you know works really\n \n\nsomething that you know works really\nwell, sure yeah, put it in the module. well, sure yeah, put it in the module. well, sure yeah, put it in the module. That's now the kind of the base\n\nThat's now the kind of the base\n \n\nThat's now the kind of the base\nassumption, the base module that others\n\nassumption, the base module that others\n \n\nassumption, the base module that others\ncan build off of. And all of DSPI is\n\ncan build off of. And all of DSPI is\n \n\ncan build off of. And all of DSPI is\nmeant to be composable, optimizable, and\n\nmeant to be composable, optimizable, and\n \n\nmeant to be composable, optimizable, and\nwhen you deconstruct your business logic\n\nwhen you deconstruct your business logic\n \n\nwhen you deconstruct your business logic\nor whatever you're trying to achieve by\n\nor whatever you're trying to achieve by\n \n\nor whatever you're trying to achieve by\nusing these different primitives, it all\n\nusing these different primitives, it all\n \n\nusing these different primitives, it all\nit's intended to kind of fit together\n\nit's intended to kind of fit together\n \n\nit's intended to kind of fit together\nand flow together. Um, and we'll get to\n\nand flow together. Um, and we'll get to\n \n\nand flow together. Um, and we'll get to\noptimizers in a minute, but at least for\n\noptimizers in a minute, but at least for\n \n\noptimizers in a minute, but at least for\nme and my team's experience, just being\n\nme and my team's experience, just being\n \n\nme and my team's experience, just being\nable to logically separate the different\n\nable to logically separate the different\n \n\nable to logically separate the different\ncomponents of a program, but basically\n\ncomponents of a program, but basically\n \n\ncomponents of a program, but basically\ninlining uh LLM calls has been\n\ninlining uh LLM calls has been\n \n\ninlining uh LLM calls has been\nincredibly powerful for us. And it's\n\nincredibly powerful for us. And it's\n \n\nincredibly powerful for us. And it's\njust an added benefit that at the end of\n\njust an added benefit that at the end of\n \n\njust an added benefit that at the end of\nthe day, because we're just kind of in\n\nthe day, because we're just kind of in\n \n\nthe day, because we're just kind of in\nthe DSPI paradigm, we happen to also be\n\nthe DSPI paradigm, we happen to also be\n \n\nthe DSPI paradigm, we happen to also be\nable to optimize it at the end of the\n\nable to optimize it at the end of the\n \n\nable to optimize it at the end of the\nday. Uh, so it comes with a bunch of\n\nday. Uh, so it comes with a bunch of\n \n\nday. Uh, so it comes with a bunch of\nstandard ones built in. I I don't use\n\nstandard ones built in. I I don't use\n \n\nstandard ones built in. I I don't use\nsome of these bottom ones as much,\n\nsome of these bottom ones as much,\n \n\nsome of these bottom ones as much,\nalthough it's they're super interesting. although it's they're super interesting. although it's they're super interesting. Um the base one at the top there is just\n\nUm the base one at the top there is just\n \n\nUm the base one at the top there is just\nDSpi.predict. DSpi.predict. DSpi.predict. That's literally just, you know, an LM\n\nThat's literally just, you know, an LM\n \n\nThat's literally just, you know, an LM\ncall. That's just uh a vanilla call. call. That's just uh a vanilla call. call. That's just uh a vanilla call. chain of thought uh probably isn't isn't\n\nchain of thought uh probably isn't isn't\n \n\nchain of thought uh probably isn't isn't\nas relevant anymore these days because\n\nas relevant anymore these days because\n \n\nas relevant anymore these days because\nmodels have kind of ironed those out but\n\nmodels have kind of ironed those out but\n \n\nmodels have kind of ironed those out but\num it is a good example of the types of\n\num it is a good example of the types of\n \n\num it is a good example of the types of\num kind of prompting techniques that can\n\num kind of prompting techniques that can\n \n\num kind of prompting techniques that can\nbe built into some of these modules um\n\nbe built into some of these modules um\n \n\nbe built into some of these modules um\nand basically all this does is add um\n\nand basically all this does is add um\n \n\nand basically all this does is add um\nsome some of the uh strings from\n\nsome some of the uh strings from\n \n\nsome some of the uh strings from\nliterature to say okay let's think step\n\nliterature to say okay let's think step\n \n\nliterature to say okay let's think step\nby step or whatever that might be same\n\nby step or whatever that might be same\n \n\nby step or whatever that might be same\nthing for react and codeact react is\n\nthing for react and codeact react is\n \n\nthing for react and codeact react is\nbasically the way that you expose the\n\nbasically the way that you expose the\n \n\nbasically the way that you expose the\ntools to the model. So, it's wrapping\n\ntools to the model. So, it's wrapping\n \n\ntools to the model."
}
] |
[
{
"role": "system",
"content": "You are an AI Engineer content creator. Write in the style of Swyx and the Latent Space podcast - technical but accessible, with practical insights about AI engineering, agents, LLMs, and developer tools. Be direct, insightful, and focus on what matters to practitioners."
},
{
"role": "user",
"content": "Share your insights on this AI engineering topic:\n\nSo, it's wrapping\nand doing some things under the hood\n\nand doing some things under the hood\n \n\nand doing some things under the hood\nwith um basically taking your signatures\n\nwith um basically taking your signatures\n \n\nwith um basically taking your signatures\nand uh it's injecting the Python\n\nand uh..."
},
{
"role": "assistant",
"content": "So, it's wrapping\nand doing some things under the hood\n\nand doing some things under the hood\n \n\nand doing some things under the hood\nwith um basically taking your signatures\n\nwith um basically taking your signatures\n \n\nwith um basically taking your signatures\nand uh it's injecting the Python\n\nand uh it's injecting the Python\n \n\nand uh it's injecting the Python\nfunctions that you've given it as tools\n\nfunctions that you've given it as tools\n \n\nfunctions that you've given it as tools\nand basically React is how you do tool\n\nand basically React is how you do tool\n \n\nand basically React is how you do tool\ncalling in DSP. calling in DSP. calling in DSP. Program with thought is uh is pretty\n\nProgram with thought is uh is pretty\n \n\nProgram with thought is uh is pretty\ncool. It kind of forces the model to\n\ncool. It kind of forces the model to\n \n\ncool. It kind of forces the model to\nthink in code and then we'll return the\n\nthink in code and then we'll return the\n \n\nthink in code and then we'll return the\nresult. Um, and you can give it a, it\n\nresult. Um, and you can give it a, it\n \n\nresult. Um, and you can give it a, it\ncomes with a Python interpreter built\n\ncomes with a Python interpreter built\n \n\ncomes with a Python interpreter built\nin, but you can give it some custom one,\n\nin, but you can give it some custom one,\n \n\nin, but you can give it some custom one,\nsome type of custom harness if you\n\nsome type of custom harness if you\n \n\nsome type of custom harness if you\nwanted to. Um, I haven't played with\n\nwanted to. Um, I haven't played with\n \n\nwanted to. Um, I haven't played with\nthat one too too much, but it is super\n\nthat one too too much, but it is super\n \n\nthat one too too much, but it is super\ninteresting. If you have like a highly\n\ninteresting. If you have like a highly\n \n\ninteresting. If you have like a highly\ntechnical problem or workflow or\n\ntechnical problem or workflow or\n \n\ntechnical problem or workflow or\nsomething like that where you want the\n\nsomething like that where you want the\n \n\nsomething like that where you want the\nmodel to inject reasoning in code at\n\nmodel to inject reasoning in code at\n \n\nmodel to inject reasoning in code at\ncertain parts of your pipeline, that's\n\ncertain parts of your pipeline, that's\n \n\ncertain parts of your pipeline, that's\nthat's kind of an really easy way to do\n\nthat's kind of an really easy way to do\n \n\nthat's kind of an really easy way to do\nit. And then some of these other ones\n\nit. And then some of these other ones\n \n\nit. And then some of these other ones\nare basically just different\n\nare basically just different\n \n\nare basically just different\nmethodologies for comparing outputs or\n\nmethodologies for comparing outputs or\n \n\nmethodologies for comparing outputs or\nrunning things in parallel. running things in parallel. running things in parallel. So here's what one looks like. Again,\n\nSo here's what one looks like. Again,\n \n\nSo here's what one looks like. Again,\nit's it's fairly simple. It's, you know,\n\nit's it's fairly simple. It's, you know,\n \n\nit's it's fairly simple. It's, you know,\nit is a Python class at the end of the\n\nit is a Python class at the end of the\n \n\nit is a Python class at the end of the\nday. Um, and so you do some initial\n\nday. Um, and so you do some initial\n \n\nday. Um, and so you do some initial\ninitialization up top. In this case,\n\ninitialization up top. In this case,\n \n\ninitialization up top. In this case,\nyou're seeing the uh\n\nyou're seeing the uh\n \n\nyou're seeing the uh\nuh the shorthand signature up there. So,\n\nuh the shorthand signature up there. So,\n \n\nuh the shorthand signature up there. So,\nI'm this module uh just to give you some\n\nI'm this module uh just to give you some\n \n\nI'm this module uh just to give you some\ncontext is an excerpt from um one of the\n\ncontext is an excerpt from um one of the\n \n\ncontext is an excerpt from um one of the\nthe Python um files that's in the repo\n\nthe Python um files that's in the repo\n \n\nthe Python um files that's in the repo\nis basically taking in a bunch of time\n\nis basically taking in a bunch of time\n \n\nis basically taking in a bunch of time\nentries and making sure that they adhere\n\nentries and making sure that they adhere\n \n\nentries and making sure that they adhere\nto certain standards, making sure that\n\nto certain standards, making sure that\n \n\nto certain standards, making sure that\nthings are capitalized properly or that\n\nthings are capitalized properly or that\n \n\nthings are capitalized properly or that\nthere are periods at the end of the\n\nthere are periods at the end of the\n \n\nthere are periods at the end of the\nsentences or whatever it might be. sentences or whatever it might be. sentences or whatever it might be. that's from a real client use case where\n\nthat's from a real client use case where\n \n\nthat's from a real client use case where\nthey had hundreds of thousands of time\n\nthey had hundreds of thousands of time\n \n\nthey had hundreds of thousands of time\nentries and they needed to make sure\n\nentries and they needed to make sure\n \n\nentries and they needed to make sure\nthat they all adhere to the same format. that they all adhere to the same format. that they all adhere to the same format. This was one way to to kind of do that\n\nThis was one way to to kind of do that\n \n\nThis was one way to to kind of do that\nvery elegantly, at least in my opinion,\n\nvery elegantly, at least in my opinion,\n \n\nvery elegantly, at least in my opinion,\nwas taking up top you can define the the\n\nwas taking up top you can define the the\n \n\nwas taking up top you can define the the\nsignature. It's adding the some\n\nsignature. It's adding the some\n \n\nsignature. It's adding the some\nadditional instructions that were\n\nadditional instructions that were\n \n\nadditional instructions that were\ndefined elsewhere and then saying for\n\ndefined elsewhere and then saying for\n \n\ndefined elsewhere and then saying for\nthis module the the change tense um call\n\nthis module the the change tense um call\n \n\nthis module the the change tense um call\nis going to be just a vanilla predict\n\nis going to be just a vanilla predict\n \n\nis going to be just a vanilla predict\ncall. And then when you actually call\n\ncall. And then when you actually call\n \n\ncall. And then when you actually call\nthe module, you enter into the forward\n\nthe module, you enter into the forward\n \n\nthe module, you enter into the forward\nfunction which you can inter basically\n\nfunction which you can inter basically\n \n\nfunction which you can inter basically\nintersperse the LLM call which would be\n\nintersperse the LLM call which would be\n \n\nintersperse the LLM call which would be\nthe first one and then do some kind of\n\nthe first one and then do some kind of\n \n\nthe first one and then do some kind of\nhard-coded business logic beneath it. hard-coded business logic beneath it. hard-coded business logic beneath it. Uh tools as I mentioned before these are\n\nUh tools as I mentioned before these are\n \n\nUh tools as I mentioned before these are\njust vanilla kind of Python functions. just vanilla kind of Python functions. just vanilla kind of Python functions. It's the DSP's tool interface. So under\n\nIt's the DSP's tool interface. So under\n \n\nIt's the DSP's tool interface. So under\nthe hood, DSPI uses light LLM. And so\n\nthe hood, DSPI uses light LLM. And so\n \n\nthe hood, DSPI uses light LLM. And so\nthere needs to be some kind of coupling\n\nthere needs to be some kind of coupling\n \n\nthere needs to be some kind of coupling\nbetween the two, but fundamentally um\n\nbetween the two, but fundamentally um\n \n\nbetween the two, but fundamentally um\nany type of tool that would that you\n\nany type of tool that would that you\n \n\nany type of tool that would that you\nwould use elsewhere, you can also use in\n\nwould use elsewhere, you can also use in\n \n\nwould use elsewhere, you can also use in\nin DSPI. And this is probably obvious to\n\nin DSPI. And this is probably obvious to\n \n\nin DSPI. And this is probably obvious to\nmost of you, but here's just an example. most of you, but here's just an example. most of you, but here's just an example. You have two functions, get weather,\n\nYou have two functions, get weather,\n \n\nYou have two functions, get weather,\nsearch web. You include that with a\n\nsearch web."
}
] |
[
{
"role": "system",
"content": "You are an AI Engineer content creator. Write in the style of Swyx and the Latent Space podcast - technical but accessible, with practical insights about AI engineering, agents, LLMs, and developer tools. Be direct, insightful, and focus on what matters to practitioners."
},
{
"role": "user",
"content": "Share your insights on this AI engineering topic:\n\nYou include that with a\n \n\nsearch web. You include that with a\nsignature. So in this case, I'm saying\n\nsignature. So in this case, I'm saying\n \n\nsignature. So in this case, I'm saying\nthe signature is I'm going to give you a\n\nthe signature is I'm going to give you a\n \n\nthe signature is I'm going to ..."
},
{
"role": "assistant",
"content": "You include that with a\n \n\nsearch web. You include that with a\nsignature. So in this case, I'm saying\n\nsignature. So in this case, I'm saying\n \n\nsignature. So in this case, I'm saying\nthe signature is I'm going to give you a\n\nthe signature is I'm going to give you a\n \n\nthe signature is I'm going to give you a\nquestion. please give me an answer. I'm\n\nquestion. please give me an answer. I'm\n \n\nquestion. please give me an answer. I'm\nnot even specifying the types. It's just\n\nnot even specifying the types. It's just\n \n\nnot even specifying the types. It's just\ngoing to infer what that means. Uh I'm\n\ngoing to infer what that means. Uh I'm\n \n\ngoing to infer what that means. Uh I'm\ngiving it the get weather and the search\n\ngiving it the get weather and the search\n \n\ngiving it the get weather and the search\nweb tools and I'm saying, okay, do your\n\nweb tools and I'm saying, okay, do your\n \n\nweb tools and I'm saying, okay, do your\nthing, but only go five rounds just so\n\nthing, but only go five rounds just so\n \n\nthing, but only go five rounds just so\nit doesn't spin off and do something\n\nit doesn't spin off and do something\n \n\nit doesn't spin off and do something\ncrazy. And then a call here is literally\n\ncrazy. And then a call here is literally\n \n\ncrazy. And then a call here is literally\njust calling the React agent that I\n\njust calling the React agent that I\n \n\njust calling the React agent that I\ncreated above with the question, what's\n\ncreated above with the question, what's\n \n\ncreated above with the question, what's\nthe weather like in Tokyo? We'll see an\n\nthe weather like in Tokyo? We'll see an\n \n\nthe weather like in Tokyo? We'll see an\nexample of this in the code session, but\n\nexample of this in the code session, but\n \n\nexample of this in the code session, but\nbasically what this would do is give the\n\nbasically what this would do is give the\n \n\nbasically what this would do is give the\nmodel the prompt, the tools, and let it\n\nmodel the prompt, the tools, and let it\n \n\nmodel the prompt, the tools, and let it\ndo its thing. do its thing. do its thing. So adapters, before I cover this a\n\nSo adapters, before I cover this a\n \n\nSo adapters, before I cover this a\nlittle bit, they're basically prompt\n\nlittle bit, they're basically prompt\n \n\nlittle bit, they're basically prompt\nformatterers, if you will. So the\n\nformatterers, if you will. So the\n \n\nformatterers, if you will. So the\ndescription from the docs probably says\n\ndescription from the docs probably says\n \n\ndescription from the docs probably says\nit best. It's you know it takes your\n\nit best. It's you know it takes your\n \n\nit best. It's you know it takes your\nsignature the inputs other attributes\n\nsignature the inputs other attributes\n \n\nsignature the inputs other attributes\nand it converts them into some type of\n\nand it converts them into some type of\n \n\nand it converts them into some type of\nmessage format that you have specified\n\nmessage format that you have specified\n \n\nmessage format that you have specified\nor that the adapter has specified and so\n\nor that the adapter has specified and so\n \n\nor that the adapter has specified and so\nas an example the JSON adapter taking\n\nas an example the JSON adapter taking\n \n\nas an example the JSON adapter taking\nsay a pyantic object that we defined\n\nsay a pyantic object that we defined\n \n\nsay a pyantic object that we defined\nbefore this is the actual prompt that's\n\nbefore this is the actual prompt that's\n \n\nbefore this is the actual prompt that's\nsent into the LLM and so you can see the\n\nsent into the LLM and so you can see the\n \n\nsent into the LLM and so you can see the\ninput fields so this would have been\n\ninput fields so this would have been\n \n\ninput fields so this would have been\ndefined as okay clinical note type\n\ndefined as okay clinical note type\n \n\ndefined as okay clinical note type\nstring patient info as a patient details\n\nstring patient info as a patient details\n \n\nstring patient info as a patient details\nobject object which which would have\n\nobject object which which would have\n \n\nobject object which which would have\nbeen defined elsewhere and then this is\n\nbeen defined elsewhere and then this is\n \n\nbeen defined elsewhere and then this is\nthe definition of the patient info. It's\n\nthe definition of the patient info. It's\n \n\nthe definition of the patient info. It's\nbasically a JSON dump of that pantic\n\nbasically a JSON dump of that pantic\n \n\nbasically a JSON dump of that pantic\nobject. Go ahead. object. Go ahead. object. Go ahead. >> So this idea there's like a base adapter\n\n>> So this idea there's like a base adapter\n \n\n>> So this idea there's like a base adapter\ndefault that's good for most cases and\n\ndefault that's good for most cases and\n \n\ndefault that's good for most cases and\nthis is if you want to tweak that to do\n\nthis is if you want to tweak that to do\n \n\nthis is if you want to tweak that to do\nsomething more specific. something more specific. something more specific. >> That's right. >> That's right. >> That's right. >> Yeah. The question was if if there's a\n\n>> Yeah. The question was if if there's a\n \n\n>> Yeah. The question was if if there's a\nbase adapter and would this be an\n\nbase adapter and would this be an\n \n\nbase adapter and would this be an\nexample of where you want to do\n\nexample of where you want to do\n \n\nexample of where you want to do\nsomething specific? Answer is yes. So um\n\nsomething specific? Answer is yes. So um\n \n\nsomething specific? Answer is yes. So um\nit's a guy pashant who is um I have his\n\nit's a guy pashant who is um I have his\n \n\nit's a guy pashant who is um I have his\nTwitter at the end of this presentation\n\nTwitter at the end of this presentation\n \n\nTwitter at the end of this presentation\nbut he's been great. [clears throat] He\n\nbut he's been great. [clears throat] He\n \n\nbut he's been great. [clears throat] He\ndid some testing comparing the JSON\n\ndid some testing comparing the JSON\n \n\ndid some testing comparing the JSON\nadapter with the BAML adapter. Um and\n\nadapter with the BAML adapter. Um and\n \n\nadapter with the BAML adapter. Um and\nyou can see just intuitively even even\n\nyou can see just intuitively even even\n \n\nyou can see just intuitively even even\nfor us humans the way that this is\n\nfor us humans the way that this is\n \n\nfor us humans the way that this is\nformatted is a little bit more\n\nformatted is a little bit more\n \n\nformatted is a little bit more\nintuitive. It's probably more token\n\nintuitive. It's probably more token\n \n\nintuitive. It's probably more token\nefficient too just considering like if\n\nefficient too just considering like if\n \n\nefficient too just considering like if\nyou look at the messy JSON that's here\n\nyou look at the messy JSON that's here\n \n\nyou look at the messy JSON that's here\nversus the I guess slightly better\n\nversus the I guess slightly better\n \n\nversus the I guess slightly better\nformatted BAML that's here. um can\n\nformatted BAML that's here. um can\n \n\nformatted BAML that's here. um can\nactually improve performance by you know\n\nactually improve performance by you know\n \n\nactually improve performance by you know\nfive to 10 percent depending on your use\n\nfive to 10 percent depending on your use\n \n\nfive to 10 percent depending on your use\ncase. So it's a good example of how you\n\ncase. So it's a good example of how you\n \n\ncase. So it's a good example of how you\ncan format things differently. The the\n\ncan format things differently. The the\n \n\ncan format things differently. The the\nrest of the program wouldn't have\n\nrest of the program wouldn't have\n \n\nrest of the program wouldn't have\nchanged at all. You just specify the\n\nchanged at all. You just specify the\n \n\nchanged at all. You just specify the\nBAML adapter and it totally changes how\n\nBAML adapter and it totally changes how\n \n\nBAML adapter and it totally changes how\nthe information is presented under the\n\nthe information is presented under the\n \n\nthe information is presented under the\nhood to the LLM\n\nhood to the LLM\n \n\nhood to the LLM\nmultimodality. I mean this obviously is\n\nmultimodality. I mean this obviously is\n \n\nmultimodality. I mean this obviously is\nmore at the model level but DSPI\n\nmore at the model level but DSPI\n \n\nmore at the model level but DSPI\nsupports multiple modalities by default. supports multiple modalities by default. supports multiple modalities by default. So images, audio, some others."
}
] |
[
{
"role": "system",
"content": "You are an AI Engineer content creator. Write in the style of Swyx and the Latent Space podcast - technical but accessible, with practical insights about AI engineering, agents, LLMs, and developer tools. Be direct, insightful, and focus on what matters to practitioners."
},
{
"role": "user",
"content": "Share your insights on this AI engineering topic:\n\nUm, and\n\nSo images, audio, some others. Um, and\n \n\nSo images, audio, some others. Um, and\nthe same type of thing, you kind of just\n\nthe same type of thing, you kind of just\n \n\nthe same type of thing, you kind of just\nfeed it in as part of your signature and\n\nfeed it in as part of your signature and\n..."
},
{
"role": "assistant",
"content": "Um, and\n\nSo images, audio, some others. Um, and\n \n\nSo images, audio, some others. Um, and\nthe same type of thing, you kind of just\n\nthe same type of thing, you kind of just\n \n\nthe same type of thing, you kind of just\nfeed it in as part of your signature and\n\nfeed it in as part of your signature and\n \n\nfeed it in as part of your signature and\nthen you can get some very nice clean\n\nthen you can get some very nice clean\n \n\nthen you can get some very nice clean\noutput. This allows you to work with\n\noutput. This allows you to work with\n \n\noutput. This allows you to work with\nthem very, very, very easily, very\n\nthem very, very, very easily, very\n \n\nthem very, very, very easily, very\nquickly. And for those uh, eagle-eyed\n\nquickly. And for those uh, eagle-eyed\n \n\nquickly. And for those uh, eagle-eyed\nparticipants, you can see the first uh,\n\nparticipants, you can see the first uh,\n \n\nparticipants, you can see the first uh,\nlineup there is attachments. It's\n\nlineup there is attachments. It's\n \n\nlineup there is attachments. It's\nprobably a lesserk known library. probably a lesserk known library. probably a lesserk known library. Another guy on Twitter is awesome. Uh,\n\nAnother guy on Twitter is awesome. Uh,\n \n\nAnother guy on Twitter is awesome. Uh,\nMaxim, I think it is. uh he created this\n\nMaxim, I think it is. uh he created this\n \n\nMaxim, I think it is. uh he created this\nlibrary that just is basically a\n\nlibrary that just is basically a\n \n\nlibrary that just is basically a\ncatch-all for working with different\n\ncatch-all for working with different\n \n\ncatch-all for working with different\ntypes of files and converting them into\n\ntypes of files and converting them into\n \n\ntypes of files and converting them into\na format that's super easy to use with\n\na format that's super easy to use with\n \n\na format that's super easy to use with\nLLMs. Um he's a big DSPI fan as well. So\n\nLLMs. Um he's a big DSPI fan as well. So\n \n\nLLMs. Um he's a big DSPI fan as well. So\nhe made basically an adapter that's\n\nhe made basically an adapter that's\n \n\nhe made basically an adapter that's\nspecific to this. But that's all it\n\nspecific to this. But that's all it\n \n\nspecific to this. But that's all it\ntakes to pull in images, PDFs, whatever\n\ntakes to pull in images, PDFs, whatever\n \n\ntakes to pull in images, PDFs, whatever\nit might be. You'll see some examples of\n\nit might be. You'll see some examples of\n \n\nit might be. You'll see some examples of\nthat and it just makes at least has made\n\nthat and it just makes at least has made\n \n\nthat and it just makes at least has made\nmy life super super easy. my life super super easy. my life super super easy. Here's another example of the same sort\n\nHere's another example of the same sort\n \n\nHere's another example of the same sort\nof thing. So this is a PDF of a form 4\n\nof thing. So this is a PDF of a form 4\n \n\nof thing. So this is a PDF of a form 4\nform. So, you know, public SEC form from\n\nform. So, you know, public SEC form from\n \n\nform. So, you know, public SEC form from\nNvidia. Nvidia. Nvidia. Um, up top I'm just giving it the link. Um, up top I'm just giving it the link. Um, up top I'm just giving it the link. I'm saying, okay, attachments, do your\n\nI'm saying, okay, attachments, do your\n \n\nI'm saying, okay, attachments, do your\nthing. Pull it down, create images,\n\nthing. Pull it down, create images,\n \n\nthing. Pull it down, create images,\nwhatever you're going to do. I don't\n\nwhatever you're going to do. I don't\n \n\nwhatever you're going to do. I don't\nneed to worry about it. I don't care\n\nneed to worry about it. I don't care\n \n\nneed to worry about it. I don't care\nabout it. This is super simple rag, but\n\nabout it. This is super simple rag, but\n \n\nabout it. This is super simple rag, but\nbasically, okay, I want to do rag over\n\nbasically, okay, I want to do rag over\n \n\nbasically, okay, I want to do rag over\nthis document. I'm going to give you a\n\nthis document. I'm going to give you a\n \n\nthis document. I'm going to give you a\nquestion. I'm going to give you the\n\nquestion. I'm going to give you the\n \n\nquestion. I'm going to give you the\ndocument and I want the answer. Um, and\n\ndocument and I want the answer. Um, and\n \n\ndocument and I want the answer. Um, and\nyou can see how simple that is. you can see how simple that is. you can see how simple that is. Literally just feeding in the document. Literally just feeding in the document. Literally just feeding in the document. How many shares were sold? Interestingly\n\nHow many shares were sold? Interestingly\n \n\nHow many shares were sold? Interestingly\nhere, I'm not sure if it's super easy to\n\nhere, I'm not sure if it's super easy to\n \n\nhere, I'm not sure if it's super easy to\nsee, but you actually have two\n\nsee, but you actually have two\n \n\nsee, but you actually have two\ntransactions\n\ntransactions\n \n\ntransactions\nhere. So, it's going to have to do some\n\nhere. So, it's going to have to do some\n \n\nhere. So, it's going to have to do some\nmath likely under the hood. And you can\n\nmath likely under the hood. And you can\n \n\nmath likely under the hood. And you can\nsee here the thinking and the the\n\nsee here the thinking and the the\n \n\nsee here the thinking and the the\nultimate answer. Go ahead. ultimate answer. Go ahead. ultimate answer. Go ahead. >> Is it on the rag step? Is it creating a\n\n>> Is it on the rag step? Is it creating a\n \n\n>> Is it on the rag step? Is it creating a\nvector store of some kind or creating\n\nvector store of some kind or creating\n \n\nvector store of some kind or creating\nembeddings and searching over those? Is\n\nembeddings and searching over those? Is\n \n\nembeddings and searching over those? Is\nthere a bunch going on in the background\n\nthere a bunch going on in the background\n \n\nthere a bunch going on in the background\nthere or what? there or what? there or what? >> This is poor man's rack. I should have\n\n>> This is poor man's rack. I should have\n \n\n>> This is poor man's rack. I should have\nclarified. This is this is literally\n\nclarified. This is this is literally\n \n\nclarified. This is this is literally\njust pulling in the document images and\n\njust pulling in the document images and\n \n\njust pulling in the document images and\nI think attachments will do some basic\n\nI think attachments will do some basic\n \n\nI think attachments will do some basic\nOCR under the hood. Um, but it doesn't\n\nOCR under the hood. Um, but it doesn't\n \n\nOCR under the hood. Um, but it doesn't\ndo anything other than that. That's it. do anything other than that. That's it. do anything other than that. That's it. All we're feeding in here, the the\n\nAll we're feeding in here, the the\n \n\nAll we're feeding in here, the the\nactual document object that's being fed\n\nactual document object that's being fed\n \n\nactual document object that's being fed\nin, yeah, is literally just the text\n\nin, yeah, is literally just the text\n \n\nin, yeah, is literally just the text\nthat's been OCRD. the images, the model\n\nthat's been OCRD. the images, the model\n \n\nthat's been OCRD. the images, the model\ndoes the rest. does the rest. does the rest. [sighs] All right, so optimizers uh\n\n[sighs] All right, so optimizers uh\n \n\n[sighs] All right, so optimizers uh\nlet's see how we're doing. Okay. Um\n\nlet's see how we're doing. Okay. Um\n \n\nlet's see how we're doing. Okay. Um\noptimizers are super powerful, super\n\noptimizers are super powerful, super\n \n\noptimizers are super powerful, super\ninteresting concept. It's been some\n\ninteresting concept. It's been some\n \n\ninteresting concept. It's been some\nresearch um that argues I think that\n\nresearch um that argues I think that\n \n\nresearch um that argues I think that\nit's just as performant if not in cert\n\nit's just as performant if not in cert\n \n\nit's just as performant if not in cert\nin certain situations more performant\n\nin certain situations more performant\n \n\nin certain situations more performant\nthan fine-tuning would be for certain\n\nthan fine-tuning would be for certain\n \n\nthan fine-tuning would be for certain\nmodels for certain situations. there's\n\nmodels for certain situations. there's\n \n\nmodels for certain situations. there's\nall this research about in context\n\nall this research about in context\n \n\nall this research about in context\nlearning and such. And so whether you\n\nlearning and such."
}
] |
End of preview. Expand
in Data Studio
README.md exists but content is empty.
- Downloads last month
- 14