prompt stringlengths 324 9.71k | target stringlengths 323 4.03k | meta_json stringlengths 147 171 | format stringclasses 1
value |
|---|---|---|---|
Below is an earlier comment by Ryan Greenblatt in a LessWrong thread. Write Ryan's follow-up comment in the same thread (a clarification, self-reply, or response to an unseen interlocutor).
Earlier Ryan comment:
> It doesn't seem unreasonable to me to suggest that literally saving billions of lives is worth pursuing e... | To be clear, I agree there are reasonable values which result in someone thinking accelerating AI now is good and values+beliefs which result in thinking a pause wouldn't good in likely circumstances.
And I don't think cryonics makes much of a difference to the bottom line. (I think ultra low cost cryonics might make ... | {"comment_id": "23f8LkTcdbcp3eE58", "format": "dialogue", "parent_id": "qCQ2joMmb4fAgz4oL", "parent_kind": "ryan_self_thread", "post_id": "h45ngW5guruD7tS4b"} | dialogue |
Below is an earlier comment by Ryan Greenblatt in a LessWrong thread. Write Ryan's follow-up comment in the same thread (a clarification, self-reply, or response to an unseen interlocutor).
Earlier Ryan comment:
> phrases like "the evidence suggests that if the current ML systems were trying to deceive us, we wouldn't... | (Separately, I think there are a few important caveats with this work. In particular, the backdoor trigger is extremely simple (a single fixed token) and the model doesn't really have to do any "reasoning" about when or how to strike. It plausible that experiments with these additional properties would imply that curre... | {"comment_id": "fknjgZa6Lmbiyyxah", "format": "dialogue", "parent_id": "jpRdaYznvrjWQdcah", "parent_kind": "ryan_self_thread", "post_id": "ZAsJv7xijKTfZkMtr"} | dialogue |
Below is an earlier comment by Ryan Greenblatt in a LessWrong thread. Write Ryan's follow-up comment in the same thread (a clarification, self-reply, or response to an unseen interlocutor).
Earlier Ryan comment:
Are you claiming that future powerful AIs won't be well described as pursuing goals (aka being goal-directe... | (Separately, I was confused by the original footnote. Is Alex claiming that deconfusing goal-directedness is a thing that no one has tried to do? (Seems wrong so probably not?) Or that it's strange to be worried when the argument for worry depends on something so fuzzy that you need to deconfuse it? I think the second ... | {"comment_id": "wTd67oQDHHFHinDXh", "format": "dialogue", "parent_id": "XqxzGktE9WuxdkLAF", "parent_kind": "ryan_self_thread", "post_id": "yxWbbe9XcgLFCrwiL"} | dialogue |
Below is an earlier comment by Ryan Greenblatt in a LessWrong thread. Write Ryan's follow-up comment in the same thread (a clarification, self-reply, or response to an unseen interlocutor).
Earlier Ryan comment:
> beyond what was capable with Meta's finetuning
How do you know this is beyond what finetuning was capabl... | I was being foolish, the vectors are averaged across a dataset, but there are still positive vs negative contrast pairs, so we should see sample efficiency improvements from contrast pairs (it is generally the case that contrast pairs are more sample efficient). That said, I'm unsure if simple techniques like DPO are j... | {"comment_id": "tqbCGFvGPDsaXpyvh", "format": "dialogue", "parent_id": "r4ZGs8Jao3YF9kD78", "parent_kind": "ryan_self_thread", "post_id": "raoeNarFYCxxyKAop"} | dialogue |
Below is an earlier comment by Ryan Greenblatt in a LessWrong thread. Write Ryan's follow-up comment in the same thread (a clarification, self-reply, or response to an unseen interlocutor).
Earlier Ryan comment:
> building misaligned smarter-than-human systems will kill everyone, including their children [...] if they... | Here's another way to frame why this matters.
When you make a claim like "misaligned AIs kill literally everyone", then reasonable people will be like "but will they?" and you should be a in a position where you can defend this claim. But actually, MIRI doesn't really want to defend this claim against the best objecti... | {"comment_id": "FAjJrQDzLkAHZk423", "format": "dialogue", "parent_id": "xBYimQtgASti5tgWv", "parent_kind": "ryan_self_thread", "post_id": "tKk37BFkMzchtZThx"} | dialogue |
Below is an earlier comment by Ryan Greenblatt in a LessWrong thread. Write Ryan's follow-up comment in the same thread (a clarification, self-reply, or response to an unseen interlocutor).
Earlier Ryan comment:
> - A capabilities evaluation is defined as “a model evaluation designed to test whether a model could do s... | I sometimes refer to capability based arguments as *control arguments*.
Then, we can name two lines of defense:
- The control line of defense: Would the AI succeed at causing bad outcomes if it tried?
- The propensity line of defense: Would the AI try to cause bad outcomes?
It's possible to develop techniques which ... | {"comment_id": "nAcCWYX2RioQzWoTM", "format": "dialogue", "parent_id": "PhfDvfu9N27FHkoYt", "parent_kind": "ryan_self_thread", "post_id": "mcnWZBnbeDz7KKtjJ"} | dialogue |
Below is an earlier comment by Ryan Greenblatt in a LessWrong thread. Write Ryan's follow-up comment in the same thread (a clarification, self-reply, or response to an unseen interlocutor).
Earlier Ryan comment:
On sample efficiency and generalization more broadly, I now overall think something like:
- Using contrast... | Due to the results [noted in in TurnTrout's comment here from Liu et al.](https://www.lesswrong.com/posts/raoeNarFYCxxyKAop/modulating-sycophancy-in-an-rlhf-model-via-activation?commentId=ZFcCoadnwRms8EPhA), I now don't think the action is mostly coming from contrast pairs (in at least some cases).
So, there is higher... | {"comment_id": "96mN873CGM8QMfdGb", "format": "dialogue", "parent_id": "zJMiewZLcy4jatmeR", "parent_kind": "ryan_self_thread", "post_id": "raoeNarFYCxxyKAop"} | dialogue |
Below is an earlier comment by Ryan Greenblatt in a LessWrong thread. Write Ryan's follow-up comment in the same thread (a clarification, self-reply, or response to an unseen interlocutor).
Earlier Ryan comment:
For mechanistic interpretabilty, very ambitious success looks something like:
- Have some decomposition of... | The main reason why I think mechanistic interpretability is very far from ambitious success is that current _numbers_ are extremely bad and what people explain is extremely cherry picked. Like people's explanations typically result in performance which is worse than that of much, much tinier models even though heavy ch... | {"comment_id": "Npzm3cfgQxtyha84z", "format": "dialogue", "parent_id": "wmxZwAHZrnyaytpnr", "parent_kind": "ryan_self_thread", "post_id": "LNA8mubrByG7SFacm"} | dialogue |
Below is an earlier comment by Ryan Greenblatt in a LessWrong thread. Write Ryan's follow-up comment in the same thread (a clarification, self-reply, or response to an unseen interlocutor).
Earlier Ryan comment:
I would summarize this result as:
If you train models to say "there is a reason I should insert a vulnerab... | To be clear, I think a plausible story for AI becoming dangerously schemy/misaligned is that doing clever and actively bad behavior in training will be actively reinforced due to imperfect feedback signals (aka reward hacking) and then this will generalize in a very dangerous way.
So, I am interested in the question o... | {"comment_id": "kuHurc5MDkH5YZa25", "format": "dialogue", "parent_id": "Zb4JMYkEuJgx4SZpr", "parent_kind": "ryan_self_thread", "post_id": "ukTLGe5CQq9w8FMne"} | dialogue |
Below is an earlier comment by Ryan Greenblatt in a LessWrong thread. Write Ryan's follow-up comment in the same thread (a clarification, self-reply, or response to an unseen interlocutor).
Earlier Ryan comment:
This is a great post on the topic which I ~~pretty much entirely~~ mostly agree with. Thanks for writing th... | Some more notes:
- We shouldn't expect that we get a huge win from AIs which are anthropically muggable, as discussed in [Can we get more than this?](https://www.lesswrong.com/posts/ZLAnH5epD8TmotZHj/you-can-in-fact-bamboozle-an-unaligned-ai-into-sparing-your?commentId=djsDxRnx7cMoochKn#Can_we_get_more_than_this_), b... | {"comment_id": "zN6BtY9Xsz3qcm7nn", "format": "dialogue", "parent_id": "xQWSbQ68Q75Mp9Edt", "parent_kind": "ryan_self_thread", "post_id": "ZLAnH5epD8TmotZHj"} | dialogue |
Below is an earlier comment by Ryan Greenblatt in a LessWrong thread. Write Ryan's follow-up comment in the same thread (a clarification, self-reply, or response to an unseen interlocutor).
Earlier Ryan comment:
> Also on generalization, if you just train your AI system to be honest in the easy cases (where you know w... | > What about cases where the AI would be able to seize vast amounts of power and humans no longer understand what's going on?
Maybe this is fine because you can continuously adjust to real deployment regimes with crazy powerful AIs while still applying the training process? I'm not sure. Certainly this breaks some ho... | {"comment_id": "5SziXWrFuQTaBs98M", "format": "dialogue", "parent_id": "vxg4EqQQXkvbjCX29", "parent_kind": "ryan_self_thread", "post_id": "YbEbwYWkf8mv9jnmi"} | dialogue |
Below is an earlier comment by Ryan Greenblatt in a LessWrong thread. Write Ryan's follow-up comment in the same thread (a clarification, self-reply, or response to an unseen interlocutor).
Earlier Ryan comment:
> The strongest critique of developmental interpretability we know is the following: while it is establishe... | More generally, I wish that when people used the term "phase transition", they clarified whether they meant "s-shaped loss curves" or some more precise notion. Often, people are making a non-mechanistic claim when they say "phase transition" (we observed a loss curve with a s-shape), but there are also mechanistic clai... | {"comment_id": "8ye3KboEWFhb6uGvt", "format": "dialogue", "parent_id": "G2cGSSQ6qkgzwPApH", "parent_kind": "ryan_self_thread", "post_id": "nN7bHuHZYaWv9RDJL"} | dialogue |
Below is an earlier comment by Ryan Greenblatt in a LessWrong thread. Write Ryan's follow-up comment in the same thread (a clarification, self-reply, or response to an unseen interlocutor).
Earlier Ryan comment:
> However, even if it were practically feasible to achieve perfect alignment, I believe there would still b... | I remain interested in what a detailed scenario forecast from you looks like. A big disagreement I think we have is in how socciety will react to various choices and I think laying this out could make this more clear. (As far as what a scenario forecast from my perspective looks like, I think [@Daniel Kokotajlo](https:... | {"comment_id": "TWXd2JeMw9DxCpPDp", "format": "dialogue", "parent_id": "6eq6f555JijTLATYz", "parent_kind": "ryan_self_thread", "post_id": "KFFaKu27FNugCHFmh"} | dialogue |
Below is an earlier comment by Ryan Greenblatt in a LessWrong thread. Write Ryan's follow-up comment in the same thread (a clarification, self-reply, or response to an unseen interlocutor).
Earlier Ryan comment:
I disagree.
I think Ajeya is reasonably careful about the word reward. (Though I think I roughly disagree ... | (Another vibe disagreement I have with "without specific countermeasures" is that I think that very basic countermeasures might defeat the "pursue correlate of thing that resulted in reinforcement in an online RL context" as long as humans would have been able to recognize the dangerous actions from the AI as bad. Thus... | {"comment_id": "EimZrQGGFfFLw3xcj", "format": "dialogue", "parent_id": "jpFfKHmo4Ev2pf8hi", "parent_kind": "ryan_self_thread", "post_id": "yxWbbe9XcgLFCrwiL"} | dialogue |
Below is an earlier comment by Ryan Greenblatt in a LessWrong thread. Write Ryan's follow-up comment in the same thread (a clarification, self-reply, or response to an unseen interlocutor).
Earlier Ryan comment:
> So far, I'm confident that our proposals will not impede the vast majority of AI developers, but if we en... | Presumably, your hope for avoiding this flop threshold becoming burdensome soon is:
> As AI advances and dangerous systems become increasingly easy to develop at a fraction of the current cost, the definition of frontier AI will need to change. This is why we need an expert-led administration that can adapt the criter... | {"comment_id": "hxJugdweDjEkwvhHf", "format": "dialogue", "parent_id": "xBPpbLsgfMuee72WY", "parent_kind": "ryan_self_thread", "post_id": "unwRBRQivd2LYRfuP"} | dialogue |
Below is an earlier comment by Ryan Greenblatt in a LessWrong thread. Write Ryan's follow-up comment in the same thread (a clarification, self-reply, or response to an unseen interlocutor).
Earlier Ryan comment:
But it isn't a capabilities condition? Maybe I would be happier if you renamed this section.
Ryan's follow... | To be clear, I think there are important additional considerations related to the fact that we don't just care about capabilities that aren't covered in that section, though that section is not that far from what I would say if you renamed it to "behavioral tests", including both capabilities and alignment (that is, al... | {"comment_id": "SzPwzMz96qwCAyN3x", "format": "dialogue", "parent_id": "ZwPBae2EdimyXgiLz", "parent_kind": "ryan_self_thread", "post_id": "TTFsKxQThrqgWeXYJ"} | dialogue |
Below is an earlier comment by Ryan Greenblatt in a LessWrong thread. Write Ryan's follow-up comment in the same thread (a clarification, self-reply, or response to an unseen interlocutor).
Earlier Ryan comment:
After spending a while thinking about interpretability, my current stance is:
- Let's define *Mechanistic ... | For mechanistic interpretabilty, very ambitious success looks something like:
- Have some decomposition of the model or the behavior of the model into parts.
- For any given randomly selected part, you should almost always be able build up a very good understanding of this part in isolation.
- By "very good" I mean... | {"comment_id": "wmxZwAHZrnyaytpnr", "format": "dialogue", "parent_id": "7fNRMke9Gc4QghYyf", "parent_kind": "ryan_self_thread", "post_id": "LNA8mubrByG7SFacm"} | dialogue |
Below is an earlier comment by Ryan Greenblatt in a LessWrong thread. Write Ryan's follow-up comment in the same thread (a clarification, self-reply, or response to an unseen interlocutor).
Earlier Ryan comment:
> An H100 running FP8 calculations can do 3-4e12 FLOPs
This is incorrect.
An H100 can do 3-4e15 GP8 FLOP/... | Also you say:
> So, as a lower bound we're talking 3-4000 GPUs and as an upper bound 3-4e9. Overall, more uncertainty than LeCun's estimate but in very roughly the same ballpark.
This isn't a lower bound according to Carlsmith as he says:
> Overall, I think it **more likely than not** that 1e15 FLOP/s is enough to p... | {"comment_id": "8vLRYEMhwCEuPC7Mo", "format": "dialogue", "parent_id": "n6fvxjTbYvk3YKkiK", "parent_kind": "ryan_self_thread", "post_id": "bce63kvsAMcwxPipX"} | dialogue |
Below is an earlier comment by Ryan Greenblatt in a LessWrong thread. Write Ryan's follow-up comment in the same thread (a clarification, self-reply, or response to an unseen interlocutor).
Earlier Ryan comment:
> Here are some views, often held in a cluster:
I'm not sure exactly which clusters you're referring to, b... | I would be more sympathetic if you made a move like, "I'll accept continuity through the human range of intelligence, and that we'll only have to align systems as collectively powerful as humans, but I still think that hands-on experience is only..." In particular, I think there is a real disagreement about the relativ... | {"comment_id": "4AeTGsdzKWbAhsGss", "format": "dialogue", "parent_id": "8DqCckZ2kRMBDDoxm", "parent_kind": "ryan_self_thread", "post_id": "tNtiJp8dA6jMbgKbf"} | dialogue |
Below is an earlier comment by Ryan Greenblatt in a LessWrong thread. Write Ryan's follow-up comment in the same thread (a clarification, self-reply, or response to an unseen interlocutor).
Earlier Ryan comment:
I think this post is quite misleading and unnecessarily adversarial.
~~I'm not sure if I want to engage fu... | As an aside, I think it's good for people and organizations (especially AI labs) to clearly state their views on AI risk, see e.g., [my comment here](https://www.lesswrong.com/posts/6HEYbsqk35butCYTe/labs-should-be-explicit-about-why-they-are-building-agi?commentId=k5qEjsg2DbjaRF76m). So I agree with this aspect of the... | {"comment_id": "GwnFZf6o6JoxdxcYq", "format": "dialogue", "parent_id": "mSpR9jhmMgW9CjPMD", "parent_kind": "ryan_self_thread", "post_id": "qtTW6BFrxWw4iHcjf"} | dialogue |
Below is an earlier comment by Ryan Greenblatt in a LessWrong thread. Write Ryan's follow-up comment in the same thread (a clarification, self-reply, or response to an unseen interlocutor).
Earlier Ryan comment:
I think you're wrong about baseline elicitation sufficing.
A key difficulty is that we might need to estim... | Separately, if you want a clear red line, it's sad if relatively cheap elicitation methods which are developed can result in overshooting the line: getting people to delete model weights is considerably sadder than stopping these models from being trained. (Even though it is in principle possible to continue developing... | {"comment_id": "ppDZaX5oEtYH9iahd", "format": "dialogue", "parent_id": "Ju4TAAw9btm8jiKpg", "parent_kind": "ryan_self_thread", "post_id": "sTiKDfgFBvYyZYuiE"} | dialogue |
Below is an earlier comment by Ryan Greenblatt in a LessWrong thread. Write Ryan's follow-up comment in the same thread (a clarification, self-reply, or response to an unseen interlocutor).
Earlier Ryan comment:
The key question is whether you can find improvements which work at large scale using mostly small experime... | To be clear, I agree that reducing availability of compute will substantially slow algorithmic research. So, export controls which do a good job of reducing the available amount of compute would slow algorithmic research progress.
If we have a fixed quantity (and quality) of human researchers and reduce the amount of ... | {"comment_id": "bw5Fh3ERCaczwyFnC", "format": "dialogue", "parent_id": "iBixRcJDZnvoEZC2F", "parent_kind": "ryan_self_thread", "post_id": "qhjNejRxbMGQp4wHt"} | dialogue |
Below is an earlier comment by Ryan Greenblatt in a LessWrong thread. Write Ryan's follow-up comment in the same thread (a clarification, self-reply, or response to an unseen interlocutor).
Earlier Ryan comment:
> Suppose we condition on RLHF failing. At a high level, failures split into: (a) human labelers rewarded t... | Related to this. You say:
> I suspect this process would be much less sample efficient than vanilla RLHF, but it would have better safety properties, and measuring how much slower it is could be a good proxy for how severe the "robustness tax" is.
What specific safety properties are you thinking about?
As far as I c... | {"comment_id": "MHdciQ2ahhHk25uTF", "format": "dialogue", "parent_id": "xAyYsRJjwcd7mb5hN", "parent_kind": "ryan_self_thread", "post_id": "ncsxcf8CkDveXBCrA"} | dialogue |
Below is an earlier comment by Ryan Greenblatt in a LessWrong thread. Write Ryan's follow-up comment in the same thread (a clarification, self-reply, or response to an unseen interlocutor).
Earlier Ryan comment:
I'd guess that if you:
- Instructed human labelers to avoid sycophancy
- Gave human labelers examples of a... | More generally, I think arguments that human feedback is failing should ideally be of the form:
"Human labelers (with AI assistance) fail to notice this sort of bad behavior. Also, either this or nearby stuff can't just be resolved with trivial and obvious countermeasures like telling human labelers to be on the look ... | {"comment_id": "EEuAztJFgzgKWZCrA", "format": "dialogue", "parent_id": "54hrsJT2msPP6CaWK", "parent_kind": "ryan_self_thread", "post_id": "raoeNarFYCxxyKAop"} | dialogue |
Below is an earlier comment by Ryan Greenblatt in a LessWrong thread. Write Ryan's follow-up comment in the same thread (a clarification, self-reply, or response to an unseen interlocutor).
Earlier Ryan comment:
The key question is whether you can find improvements which work at large scale using mostly small experime... | I'm a bit confused by what's going on with the paper claiming their empirical results support innovations being compute-dependent when they only test MQA (and IMO show unclear results in this case). It almost seems like they forgot to include results or didn't realize they only tested MQA because (e.g.) they talk about... | {"comment_id": "MbpoZcnutELxBcTPW", "format": "dialogue", "parent_id": "iBixRcJDZnvoEZC2F", "parent_kind": "ryan_self_thread", "post_id": "qhjNejRxbMGQp4wHt"} | dialogue |
Below is an earlier comment by Ryan Greenblatt in a LessWrong thread. Write Ryan's follow-up comment in the same thread (a clarification, self-reply, or response to an unseen interlocutor).
Earlier Ryan comment:
> scaling up networks, running pretraining + light RLHF, probably doesn't by itself produce a schemer
I ag... | I now think there another important caveat in my views here. I was thinking about the question:
1. *Conditional on human obsoleting[^safety] AI being reached by "scaling up networks, running pretraining + light RLHF", how likely is it that that we'll end up with scheming issues?*
[^safety]: Or at least AI safety rese... | {"comment_id": "CHfNg3ygrn4cmyejj", "format": "dialogue", "parent_id": "axqBaN8NESkfqS76A", "parent_kind": "ryan_self_thread", "post_id": "yQSmcfN4kA7rATHGK"} | dialogue |
Below is an earlier comment by Ryan Greenblatt in a LessWrong thread. Write Ryan's follow-up comment in the same thread (a clarification, self-reply, or response to an unseen interlocutor).
Earlier Ryan comment:
Thanks for writing this! I appreciate the effort to make your perspective more transparent (and implicitly ... | As far as security, perhaps part of what is going on is that you expect that achieving this high bar of security is too expensive:
> ASL-4 is much more demanding and represents a rough upper limit on what we expect to be able to implement without heavily interfering with our research and deployment efforts.
My sense ... | {"comment_id": "7dE5aee5G5XFXdKHd", "format": "dialogue", "parent_id": "eCqWBjK4dgbpZ8pYT", "parent_kind": "ryan_self_thread", "post_id": "mGCcZnr4WjGjqzX5s"} | dialogue |
Below is an earlier comment by Ryan Greenblatt in a LessWrong thread. Write Ryan's follow-up comment in the same thread (a clarification, self-reply, or response to an unseen interlocutor).
Earlier Ryan comment:
> I predict that group A survives, but the humans are no longer in power. I think this illustrates the bas... | Another way to put this is that strategy stealing might not work due to technical alignment difficulties or for other reasons and I'm not sold the other reasons I've heard so far are very lethal. I do think the situation might really suck though with e.g. tons of people dying of bioweapons and with some groups that are... | {"comment_id": "nXLjjStAjwjxaT7yW", "format": "dialogue", "parent_id": "GJSdxkc7YfgdzcLRb", "parent_kind": "ryan_self_thread", "post_id": "pZhEQieM9otKXhxmd"} | dialogue |
Below is an earlier comment by Ryan Greenblatt in a LessWrong thread. Write Ryan's follow-up comment in the same thread (a clarification, self-reply, or response to an unseen interlocutor).
Earlier Ryan comment:
This is a great post on the topic which I ~~pretty much entirely~~ mostly agree with. Thanks for writing th... | To be clear, I think the exact scheme in [A proposal for humanity in the future](https://www.lesswrong.com/posts/ZLAnH5epD8TmotZHj/you-can-in-fact-bamboozle-an-unaligned-ai-into-sparing-your#A_proposal_for_humanity_in_the_Future) probably doesn't work as described because the exact level of payment is wrong and more mi... | {"comment_id": "F7Ez3wseFNoktTBwF", "format": "dialogue", "parent_id": "xQWSbQ68Q75Mp9Edt", "parent_kind": "ryan_self_thread", "post_id": "ZLAnH5epD8TmotZHj"} | dialogue |
Below is an earlier comment by Ryan Greenblatt in a LessWrong thread. Write Ryan's follow-up comment in the same thread (a clarification, self-reply, or response to an unseen interlocutor).
Earlier Ryan comment:
> Leaving aside that I'm not sure what you would 'train' the supervisor model on
I'm imagining you train i... | Another overall reaction I have to your comment:
> Security/safety is, as always, a property of the system as a whole, and not of any individual part, such as a particular model checkpoint.
Yes of course, but the key threat model under discussion here is scheming which centrally involves a specific black box individu... | {"comment_id": "ztBDpNNCeFGnx5mC8", "format": "dialogue", "parent_id": "LjzwvtxPnbmP7L2ZM", "parent_kind": "ryan_self_thread", "post_id": "yQSmcfN4kA7rATHGK"} | dialogue |
Below is an earlier comment by Ryan Greenblatt in a LessWrong thread. Write Ryan's follow-up comment in the same thread (a clarification, self-reply, or response to an unseen interlocutor).
Earlier Ryan comment:
> And I think this is also true by the vast majority of common-sense ethical views. People care about the ... | At a more basic level, I think the situation is just actually much more confusing than human extinction in a bunch of ways.
(Separately, under my views misaligned AI takeover seems *worse* than human extinction due to (e.g.) biorisk. This is because primates or other closely related seem very likely to re-evolve into ... | {"comment_id": "HGvxDGXJWSx9se8h3", "format": "dialogue", "parent_id": "xffc8ffKXWTT4YF99", "parent_kind": "ryan_self_thread", "post_id": "ZLAnH5epD8TmotZHj"} | dialogue |
Below is an earlier comment by Ryan Greenblatt in a LessWrong thread. Write Ryan's follow-up comment in the same thread (a clarification, self-reply, or response to an unseen interlocutor).
Earlier Ryan comment:
I think your discussion (and Epoch's discussion) of the CES model is confused as you aren't taking into acc... | As far as I can tell, this sort of consideration is at least somewhat damning for the literal CES model (with poor substitution) in any situation where the inputs have varied by hugely different amounts (many orders of magnitude of difference like in the compute vs labor case) and relative demand remains roughly simila... | {"comment_id": "59NufM2Nkiux6QybX", "format": "dialogue", "parent_id": "4arc3J2Z3G68rmrpi", "parent_kind": "ryan_self_thread", "post_id": "XDF6ovePBJf6hsxGj"} | dialogue |
Below is an earlier comment by Ryan Greenblatt in a LessWrong thread. Write Ryan's follow-up comment in the same thread (a clarification, self-reply, or response to an unseen interlocutor).
Earlier Ryan comment:
> I thus think its fair to say that -- empirically -- neural networks do not robustly quantify uncertainty ... | Separately, I guess I'm not that worried about failures in which the network itself doesn't "understand" what's going on. So the main issue are cases where the model in some sense knows, but doesn't report this. (E.g. ELK problems at least broadly speaking.)
I think there are bunch of issues that look sort of like thi... | {"comment_id": "apSWxC6i4wege3JL8", "format": "dialogue", "parent_id": "nEAxdNQaaNHyxzu9s", "parent_kind": "ryan_self_thread", "post_id": "wvgwYQv9B4jioqgqg"} | dialogue |
Below is a LessWrong post by Andrew Mack titled 'Mechanistically Eliciting Latent Behaviors in Language Models'.
Post body (possibly truncated):
Produced as part of the MATS Winter 2024 program, under the mentorship of Alex Turner (TurnTrout).
TL,DR: I introduce a method for eliciting latent behaviors in language mod... | Have you compared this method (finding vectors that change downstream activations as much as possible based on my understanding) with just using random vectors? (I didn't see this in the post, but I might have just missed this.)
In particular, does that yield qualitatively similar results?
Naively, I would expect tha... | {"comment_id": "mDySdqJs5wxtiXd8w", "format": "dialogue", "parent_kind": "external_post_body", "post_author": "Andrew Mack", "post_id": "ioPnHKFyy4Cw2Gr2x"} | dialogue |
Below is a LessWrong post by William_S titled 'Principles for the AGI Race'.
Post body (possibly truncated):
Crossposted from https://williamrsaunders.substack.com/p/principles-for-the-agi-race
Why form principles for the AGI Race?
I worked at OpenAI for 3 years, on the Alignment and Superalignment teams. Our goal w... | > Principle 2: Don’t take actions which impose significant risks to others without overwhelming evidence of net benefit
>
> [...]
>
> Significant margin of benefits over costs, accounting for possibility your calculations are incorrect (1.1x benefits over costs doesn’t justify, maybe 10x benefits over costs could justi... | {"comment_id": "mRBQbrREf5zgd6Ewq", "format": "dialogue", "parent_kind": "external_post_body", "post_author": "William_S", "post_id": "aRciQsjgErCf5Y7D9"} | dialogue |
Below is a LessWrong post by L Rudolf L titled 'By default, capital will matter more than ever after AGI'.
Post body (possibly truncated):
This post is crossposted from my Substack. Original here.
A modified version of this essay is now part of a much more comprehensive essay series, The Intelligence Curse.
Edited t... | This post seems to misunderstand what it is responding to and underplay a very key point: that material needs will likely be met (and selfish non-positional preferences mostly satisfied) due to extreme abundance (if humans retain control).
It mentions this offhand:
> Given sufficiently strong AI, this is not a risk a... | {"comment_id": "387PorjKkkwGSDeZ3", "format": "dialogue", "parent_kind": "external_post_body", "post_author": "L Rudolf L", "post_id": "KFFaKu27FNugCHFmh"} | dialogue |
Below is a LessWrong post by Sam Bowman titled 'The Checklist: What Succeeding at AI Safety Will Involve '.
Post body (possibly truncated):
Crossposted by habryka with Sam's permission. Expect lower probability for Sam to respond to comments here than if he had posted it (he said he'll be traveling a bunch in the comi... | > My guess is that you think heavy government involvement should occur for before/during the creation of ASL-4 systems, since you're pretty concerned about risks from ASL-4 systems being developed in non-SL5 contexts.
Yes, I think heavy government should occur once AIs can substantially accelerate general purpose R&D ... | {"comment_id": "j7XyPeJwhJAwaQyWn", "format": "dialogue", "parent_kind": "external_post_body", "post_author": "Sam Bowman", "post_id": "mGCcZnr4WjGjqzX5s"} | dialogue |
Below is a LessWrong post by Malo titled 'New Endorsements for “If Anyone Builds It, Everyone Dies”'.
Post body (possibly truncated):
Nate and Eliezer’s forthcoming book has been getting a remarkably strong reception.
I was under the impression that there are many people who find the extinction threat from AI credibl... | I think I somewhat disagree with this. My view is more like:
- The recent writings of Eliezer (and probably Nate?) are not very good at persuading thoughtful skeptics, seemingly in part due to not really trying to do this / being uninterested (see e.g. Eliezer's writing on X/twitter).
- Eliezer and Nate tried much har... | {"comment_id": "n9swTHz7hfayfzr3o", "format": "dialogue", "parent_kind": "external_post_body", "post_author": "Malo", "post_id": "khmpWJnGJnuyPdipE"} | dialogue |
Below is a LessWrong post by KatjaGrace titled 'Are we so good to simulate?'.
Post body (possibly truncated):
If you believe that,—
a) a civilization like ours is likely to survive into technological incredibleness, and
b) a technologically incredible civilization is very likely to create ‘ancestor simulations’,
—t... | I think science/trade sims for acausal trade and other purposes are likely[^reasoning] and if they occur, they likely have reasonably high measure.
My very unconfident subjective expectation for the measure on these sorts of science/trade sims is >1/100,000th (of all measure). (With massive model uncertainty due to ar... | {"comment_id": "n4DgtXrKkZatPaHKC", "format": "dialogue", "parent_kind": "external_post_body", "post_author": "KatjaGrace", "post_id": "di4Dhho4xZ4x9ABna"} | dialogue |
Below is a LessWrong post by evhub titled 'RSPs are pauses done right'.
Post body (possibly truncated):
COI: I am a research scientist at Anthropic, where I work on model organisms of misalignment; I was also involved in the drafting process for Anthropic’s RSP. Prior to joining Anthropic, I was a Research Fellow at M... | On RSPs vs pauses, my basic take is that hardcore pauses are better than RSPs and RSPs are considerably better than weak pauses.
Best: we first prevent hardware progress and stop H100 manufactoring for a bit, then we prevent AI algorithmic progress, and then we stop scaling (ideally in that order). Then, we heavily in... | {"comment_id": "2Xmativ6mgEenjG6H", "format": "dialogue", "parent_kind": "external_post_body", "post_author": "evhub", "post_id": "mcnWZBnbeDz7KKtjJ"} | dialogue |
Below is a LessWrong post by Nora Belrose titled 'Counting arguments provide no evidence for AI doom'.
Post body (possibly truncated):
Crossposted from the AI Optimists blog.
AI doom scenarios often suppose that future AIs will engage in scheming— planning to escape, gain power, and pursue ulterior motives, while dec... | > The current literature on scheming appears to have been inspired by Paul Christiano’s speculations about malign intelligences in Solomonoff induction
This doesn't seem right. The linked post by Paul here is about the (extremely speculative) case where consequentialist life emerges organically inside of full blown si... | {"comment_id": "93yj79kbkcCiYNuZ2", "format": "dialogue", "parent_kind": "external_post_body", "post_author": "Nora Belrose", "post_id": "YsFZF3K9tuzbfrLxo"} | dialogue |
Below is a LessWrong post by Benjamin_Todd titled 'How much AI inference can we do?'.
Post body (possibly truncated):
Suppose you have a bunch of GPUs. How many LLM forward passes can you do with them?[1]
This is relevant to figuring out how profitable AI will be in the short-term, how powerful AI systems might be ab... | The lower bound of "memory bandwidth vs. model size" is effectively equivalent to assuming that the batch size is a single token. I think this isn't at all close to realistic operating conditions and thus won't be a very tight lower bound. (Or reflect the most important bottlenecks.)
I think that the KV cache for a si... | {"comment_id": "BysyCtnDnq2WwCkeo", "format": "dialogue", "parent_kind": "external_post_body", "post_author": "Benjamin_Todd", "post_id": "g7H2sSGHAeYxCHzrz"} | dialogue |
Below is a LessWrong post by Elliott Thornley (EJT) titled 'The Shutdown Problem: Incomplete Preferences as a Solution'.
Post body (possibly truncated):
Preamble
This post is an updated explanation of the POST-Agents Proposal (PAP): my proposed solution to the shutdown problem.[1] The post is shorter than my AI Align... | I was asking about HSB not because I think it is similar to the process about AIs but because if the answer differs, then it implies your making some narrower assumption about the inductive biases of AI training.
> On generalizing to extremely unlikely conditionals, I think TD-agents are in much the same position as o... | {"comment_id": "jKCD3NLizgzN4BhRX", "format": "dialogue", "parent_kind": "external_post_body", "post_author": "Elliott Thornley (EJT)", "post_id": "YbEbwYWkf8mv9jnmi"} | dialogue |
Below is a LessWrong post by snewman titled 'What Indicators Should We Watch to Disambiguate AGI Timelines?'.
Post body (possibly truncated):
(Cross-post from https://amistrongeryet.substack.com/p/are-we-on-the-brink-of-agi, lightly edited for LessWrong. The original has a lengthier introduction and a bit more explana... | > top-tier/superhuman benchmark performance vs. frequent falling-flat-on-its-face real-world performance
Models are just recently getting to the point where they can complete 2 hour tasks 50% of the time in METR's tasks (at least without scaffolding that uses much more inference compute).
This isn't yet top tier perf... | {"comment_id": "r77CWogF2tpdgPdNT", "format": "dialogue", "parent_kind": "external_post_body", "post_author": "snewman", "post_id": "auGYErf5QqiTihTsJ"} | dialogue |
Below is a LessWrong post by eggsyntax titled 'LLM Generality is a Timeline Crux'.
Post body (possibly truncated):
Four-Month Update
[EDIT: I believe that this paper looking at o1-preview, which gets much better results on both blocksworld and obfuscated blocksworld, should update us significantly toward LLMs being c... | > All LLMs to date fail rather badly at classic problems of rearranging colored blocks.
It's pretty unclear to me that the LLMs do much worse than humans at this task.
They establish the humans baseline by picking one problem at random out of 600 and evaluating 50 humans on this. (Why only one problem!? It would be v... | {"comment_id": "fiy2GzwFWenCMTKSD", "format": "dialogue", "parent_kind": "external_post_body", "post_author": "eggsyntax", "post_id": "k38sJNLk7YbJA72ST"} | dialogue |
Below is a LessWrong post by Collin titled 'How "Discovering Latent Knowledge in Language Models Without Supervision" Fits Into a Broader Alignment Scheme'.
Post body (possibly truncated):
Introduction
A few collaborators and I recently released a new paper: Discovering Latent Knowledge in Language Models Without Sup... | Beyond the paper and post, I think it seems important to note the community reaction to this work. I think many people dramatically overrated the empirical results in this work due to a combination of misunderstanding what was actually done, misunderstanding why the method worked (which follow up work helped to clarify... | {"comment_id": "xXNocgoK5hvWrudJb", "format": "dialogue", "parent_kind": "external_post_body", "post_author": "Collin", "post_id": "L4anhrxjv8j2yRKKp"} | dialogue |
Below is a LessWrong post by Gunnar_Zarncke titled 'Towards Guaranteed Safe AI: A Framework for Ensuring Robust and Reliable AI Systems'.
Post body (possibly truncated):
Authors: David "davidad" Dalrymple, Joar Skalse, Yoshua Bengio, Stuart Russell, Max Tegmark, Sanjit Seshia, Steve Omohundro, Christian Szegedy, Ben G... | > However, that isn't the use-case here (the world model is not meant to be agentic).
Worth noting here that I'm mostly talking about Bengio's proposal wrt to the bayes related arguments.
And I agree that the world model isn't meant to be a schemer, but it's not as though we can guarantee that without some additional... | {"comment_id": "Ns6pzzZy9rvzLej7m", "format": "dialogue", "parent_kind": "external_post_body", "post_author": "Gunnar_Zarncke", "post_id": "wvgwYQv9B4jioqgqg"} | dialogue |
Below is a LessWrong post by Quentin FEUILLADE--MONTIXI titled 'The Stochastic Parrot Hypothesis is debatable for the last generation of LLMs'.
Post body (possibly truncated):
This post is part of a sequence on LLM Psychology.
@Pierre Peigné wrote the details section in argument 3 and the other weird phenomenon. The ... | > I assume you mean 'won't generalize to answering questions about both modalities', and that's false.
Oops, my wording was confusing. I was imagining something like having a transformer which can take in both text tokens and image tokens (patches), but each training sequence is either only images or only text. (Let's... | {"comment_id": "biJAYu9H7vzLmhdZ8", "format": "dialogue", "parent_kind": "external_post_body", "post_author": "Quentin FEUILLADE--MONTIXI", "post_id": "HxRjHq3QG8vcYy4yy"} | dialogue |
Below is a LessWrong post by Thane Ruthenis titled '"Humanity vs. AGI" Will Never Look Like "Humanity vs. AGI" to Humanity'.
Post body (possibly truncated):
When discussing AGI Risk, people often talk about it in terms of a war between humanity and an AGI. Comparisons between the amounts of resources at both sides' di... | > For what it's worth, I'm not sure which part of my scenario you are referring to here, because these are both statements I agree with.
I was arguing against:
> This story makes sense to me because I think even imperfect AIs will be a great deal for humanity. In my story, the loss of control will be gradual enough ... | {"comment_id": "M76NtfNmsu5WpRkmb", "format": "dialogue", "parent_kind": "external_post_body", "post_author": "Thane Ruthenis", "post_id": "xSJMj3Hw3D7DPy5fJ"} | dialogue |
Below is a LessWrong post by Lukas_Gloor titled 'We might be missing some key feature of AI takeoff; it\'ll probably seem like "we could\'ve seen this coming"'.
Post body (possibly truncated):
Predicting the future is hard, so it’s no surprise that we occasionally miss important developments.
However, several times r... | My guess is this is probably right given some non-trivial, but not insane countermeasures, but those countermeasures may not actually be employed in practice.
(E.g. countermeasures comparable in cost and difficulty to Google's mechanisms for ensuring security and reliability. These required substantial work and some i... | {"comment_id": "mFDJnJAnPPCiugEpz", "format": "dialogue", "parent_kind": "external_post_body", "post_author": "Lukas_Gloor", "post_id": "dLwo67p7zBuPsjG5t"} | dialogue |
Below is a LessWrong post by plex titled 'A Rocket–Interpretability Analogy'.
Post body (possibly truncated):
1.
4.4% of the US federal budget went into the space race at its peak.
This was surprising to me, until a friend pointed out that landing rockets on specific parts of the moon requires very similar technolo... | I'm pretty skeptical that Neel's MATS stream is partially supported/subsidized by GDM's desire to generally hire for capabilities . (And I certainly don't think they directly fund this.) Same for other mech interp hiring at GDM, I doubt that anyone is thinking "these mech interp employees might convert into employees f... | {"comment_id": "XhcuJn8FjgmJuTDBe", "format": "dialogue", "parent_kind": "external_post_body", "post_author": "plex", "post_id": "h4wXMXneTPDEjJ7nv"} | dialogue |
Below is a LessWrong post by orthonormal titled 'Run evals on base models too!'.
Post body (possibly truncated):
(Creating more visibility for a comment thread with Rohin Shah.)
Currently, DeepMind's capabilities evals are run on the post-RL*F (RLHF/RLAIF) models and not on the base models. This worries me because RL... | METR (formerly ARC Evals) included results on base models in their recent work ["Measuring the impact of post-training enhancements"](https://metr.github.io/autonomy-evals-guide/elicitation-gap/#3.-results) ("post-training enhancements"=elicitation). They found that GPT-4-base performed poorly in their scaffold and pro... | {"comment_id": "Xd5Ygp6iWrqjs2B7M", "format": "dialogue", "parent_kind": "external_post_body", "post_author": "orthonormal", "post_id": "dgFC394qZHgj2cWAg"} | dialogue |
Below is a LessWrong post by Steven Byrnes titled 'Foom & Doom 1: “Brain in a box in a basement”'.
Post body (possibly truncated):
1.1 Series summary and Table of Contents
This is a two-post series on AI “foom” (this post) and “doom” (next post).
A decade or two ago, it was pretty common to discuss “foom & doom” sce... | > * *LLM-focused AGI person:* “Ah, that’s true today, but eventually other AIs can do this ‘development and integration’ R&D work for us! No human labor need be involved!”
> * *Me:* “No! That’s still not radical enough! In the future, that kind of ‘development and integration’ R&D work just won’t need to be done at... | {"comment_id": "d8xg7tsKgdaZJwjkj", "format": "dialogue", "parent_kind": "external_post_body", "post_author": "Steven Byrnes", "post_id": "yew6zFWAKG4AGs3Wk"} | dialogue |
Below is a LessWrong post by So8res titled 'Apocalypse insurance, and the hardline libertarian take on AI risk'.
Post body (possibly truncated):
Short version: In a saner world, AI labs would have to purchase some sort of "apocalypse insurance", with premiums dependent on their behavior in ways that make reckless beha... | > If you imagine a hard lock on these and other such things, well that seems unrealistic to me.
I'm just trying to claim that this is possible in principle. I'm not particularly trying to argue this is realistic.
I'm just trying to argue something like "If we gave out property right to the entire universe and backcha... | {"comment_id": "4dtrs3DQMngexHnZs", "format": "dialogue", "parent_kind": "external_post_body", "post_author": "So8res", "post_id": "mSeesg7i4d9scWAet"} | dialogue |
Below is a LessWrong post by Nicholas Kross titled '[SEE NEW EDITS] No, *You* Need to Write Clearer'.
Post body (possibly truncated):
This post is aimed solely at people in AI alignment/safety.
EDIT 3 October 2023: This post did not even mention, let alone account for, how somebody should post half-baked/imperfect/ha... | > Everyone, everyone, literally everyone in AI alignment is severely wrong about at least one core thing, and disagreements still persist on seemingly-obviously-foolish things.
If by 'severely wrong about at least one core thing' you just mean 'systemically severely miscalibrated on some very important topic ', then m... | {"comment_id": "5kopfKcwui6bitbHf", "format": "dialogue", "parent_kind": "external_post_body", "post_author": "Nicholas Kross", "post_id": "mLubC65xXekk5tkug"} | dialogue |
Below is a LessWrong post by Daniel Kokotajlo titled 'Soft takeoff can still lead to decisive strategic advantage'.
Post body (possibly truncated):
[Epistemic status: Argument by analogy to historical cases. Best case scenario it's just one argument among many. Edit: Also, thanks to feedback from others, especially Pa... | It seems like there are strong reasons to expect that the post AI coalitions will look very different from the *current* world economy, though I agree that they might look like *a* world economy. For instance, imagine world GDP grows by 100x. It seems totally plausible that Google/TSMC/OpenAI revenue grows by 50x rela... | {"comment_id": "sjtD58PGdDXoBi3ad", "format": "dialogue", "parent_kind": "external_post_body", "post_author": "Daniel Kokotajlo", "post_id": "PKy8NuNPknenkDY74"} | dialogue |
Below is a LessWrong post by Daniel Kokotajlo titled 'AGI is easier than robotaxis'.
Post body (possibly truncated):
[Epistemic status: Hot take I wrote in 1 hour. We'll see in the comments how well it holds up.]
[Update: OK, seems like people hate this. I guess it was probably too hot and sloppy in retrospect. I sho... | Driving optimally might be AGI complete, but you don't necessarily need to drive optimally, it should be sufficient to beat typical human drivers for safety (this will depend on the regulatory regime of course).
It might be that the occurrences where avoiding an accident is AGI complete are lower per mile than the cas... | {"comment_id": "5w4iYdP3A5yXN9qbu", "format": "dialogue", "parent_kind": "external_post_body", "post_author": "Daniel Kokotajlo", "post_id": "A5YQqDEz9QKGAZvn6"} | dialogue |
Below is a LessWrong post by Rob Bensinger titled 'The basic reasons I expect AGI ruin'.
Post body (possibly truncated):
I've been citing AGI Ruin: A List of Lethalities to explain why the situation with AI looks lethally dangerous to me. But that post is relatively long, and emphasizes specific open technical problem... | This post seems to argue for fast/discontinuous takeoff without explicitly noting that people working in alignment often disagree. Further I think many of the arguments given here for fast takeoff seem sloppy or directly wrong on my own views.
It seems reasonable to just give your views without noting disagreement, bu... | {"comment_id": "MScxqqfwzzmrtnHfh", "format": "dialogue", "parent_kind": "external_post_body", "post_author": "Rob Bensinger", "post_id": "eaDCgdkbsfGqpWazi"} | dialogue |
Below is a LessWrong post by Rob Bensinger titled 'The Problem'.
Post body (possibly truncated):
This is a new introduction to AI as an extinction threat, previously posted to the MIRI website in February alongside a summary. It was written independently of Eliezer and Nate's forthcoming book, If Anyone Builds It, Eve... | To be clear, Buck's view is that it is a very bad outcome if a token population is kept alive (e.g., all/most currently alive humans) but (misaligned) AIs control the vast majority of resources. And, he thinks most of the badness is due to the loss of the vast majority of resources.
He didn't say "and this would be fi... | {"comment_id": "H4HLm9LpvXzJiJSAg", "format": "dialogue", "parent_kind": "external_post_body", "post_author": "Rob Bensinger", "post_id": "kgb58RL88YChkkBNf"} | dialogue |
Below is a LessWrong post by Rob Bensinger titled 'The Problem'.
Post body (possibly truncated):
This is a new introduction to AI as an extinction threat, previously posted to the MIRI website in February alongside a summary. It was written independently of Eliezer and Nate's forthcoming book, If Anyone Builds It, Eve... | My view is that we can get a bunch of improvement in safety without massive shifts to the Overton window and poorly executed attempts at shifting the Overton window with bad argumentation (or bad optics) can poison other efforts.
I think well-executed attempts at massively shifting the Overton window are great and sho... | {"comment_id": "NiexKjYnzLWdW4Tsz", "format": "dialogue", "parent_kind": "external_post_body", "post_author": "Rob Bensinger", "post_id": "kgb58RL88YChkkBNf"} | dialogue |
Below is a LessWrong post by Rob Bensinger titled 'The Problem'.
Post body (possibly truncated):
This is a new introduction to AI as an extinction threat, previously posted to the MIRI website in February alongside a summary. It was written independently of Eliezer and Nate's forthcoming book, If Anyone Builds It, Eve... | > Don't we feel gratitude and warmth and empathy and care-for-the-monkey's-values such that we're willing to make small sacrifices on their behalf?
People do make small sacrifices on behalf of monkeys? Like >1 / billion of human resources are spent on doing things for monkeys (this is just >$100k per year). And, in th... | {"comment_id": "EYjZ6GWzBPfhjAbnr", "format": "dialogue", "parent_kind": "external_post_body", "post_author": "Rob Bensinger", "post_id": "kgb58RL88YChkkBNf"} | dialogue |
Below is a LessWrong post by Elliott Thornley (EJT) titled 'The Shutdown Problem: Incomplete Preferences as a Solution'.
Post body (possibly truncated):
Preamble
This post is an updated explanation of the POST-Agents Proposal (PAP): my proposed solution to the shutdown problem.[1] The post is shorter than my AI Align... | > Also on generalization, if you just train your AI system to be honest in the easy cases (where you know what the answer to your question is), then the AI might learn the rule ‘report the truth’, but it might instead learn ‘report what my trainers believe’, or ‘report what my trainers want to hear’, or ‘report what ge... | {"comment_id": "vxg4EqQQXkvbjCX29", "format": "dialogue", "parent_kind": "external_post_body", "post_author": "Elliott Thornley (EJT)", "post_id": "YbEbwYWkf8mv9jnmi"} | dialogue |
Below is a LessWrong post by David Matolcsi titled 'You can, in fact, bamboozle an unaligned AI into sparing your life'.
Post body (possibly truncated):
There has been a renewal of discussion on how much hope we should have of an unaligned AGI leaving humanity alive on Earth after a takeover. When this topic is discu... | Here is another more narrow way to put this argument:
- Let's say Nate is 35 (arbitrary guess).
- Let's say that branches which deviated 35 years ago would pay for our branch (and other branches in our reference class). The case for this is that many people are over 50 (thus existing in both branches), and care about ... | {"comment_id": "z3wdu7vGjTibsaWdz", "format": "dialogue", "parent_kind": "external_post_body", "post_author": "David Matolcsi", "post_id": "ZLAnH5epD8TmotZHj"} | dialogue |
Below is a LessWrong post by TsviBT titled 'Views on when AGI comes and on strategy to reduce existential risk\n'.
Post body (possibly truncated):
Summary: AGI isn't super likely to come super soon. People should be working on stuff that saves humanity in worlds where AGI comes in 20 or 50 years, in addition to stuff ... | I think if you want to convince people with short timelines (e.g., 7 year medians) of your perspective, probably the most productive thing would be to better operationalize things you expect that AIs won't be able to do soon (but that AGI could do). As in, flesh out a response to [this comment](https://www.lesswrong.co... | {"comment_id": "kXc98EzmpDttrpMzt", "format": "dialogue", "parent_kind": "external_post_body", "post_author": "TsviBT", "post_id": "sTDfraZab47KiRMmT"} | dialogue |
Below is a LessWrong post by Elliott Thornley (EJT) titled 'The Shutdown Problem: Incomplete Preferences as a Solution'.
Post body (possibly truncated):
Preamble
This post is an updated explanation of the POST-Agents Proposal (PAP): my proposed solution to the shutdown problem.[1] The post is shorter than my AI Align... | > I think POST is a simple and natural rule for AIs to learn. Any kind of capable agent will have some way of comparing outcomes, and one feature of outcomes that capable agents will represent is ‘time that I remain operational’.
Do you think selectively breeding humans for this would result in this rule generalizing?... | {"comment_id": "3WxJWbChrcsaynanr", "format": "dialogue", "parent_kind": "external_post_body", "post_author": "Elliott Thornley (EJT)", "post_id": "YbEbwYWkf8mv9jnmi"} | dialogue |
Below is a LessWrong post by TurnTrout titled 'Many arguments for AI x-risk are wrong'.
Post body (possibly truncated):
The following is a lightly edited version of a memo I wrote for a retreat. It was inspired by a draft of Counting arguments provide no evidence for AI doom. I think that my post covers important poin... | I think of "light RLHF" as "RLHF which doesn't teach the model qualitatively new things, but instead just steers the model at a high level". In practice, a single round of DPO on <100,000 examples surely counts, but I'm unsure about the exact limits.
(In principle, a small amount of RL can update a model very far, I d... | {"comment_id": "5AFtejfEWAyaX6pMY", "format": "dialogue", "parent_kind": "external_post_body", "post_author": "TurnTrout", "post_id": "yQSmcfN4kA7rATHGK"} | dialogue |
Below is a LessWrong post by Sam Marks titled 'What’s up with LLMs representing XORs of arbitrary features?'.
Post body (possibly truncated):
Thanks to Clément Dumas, Nikola Jurković, Nora Belrose, Arthur Conmy, and Oam Patel for feedback.
In the comments of the post on Google Deepmind’s CCS challenges paper, I expre... | Yes, that's what I'm saying. I think this is right? Note that we only need salience on one side between false and true, so "true vs false" is salient as long as "false" is salient. I would guess that "this is false" is very salient for this type of data even for a normal pretrained LLM.
(Similarly, "this is english" i... | {"comment_id": "Gn9iWpZbPxTuWKgAk", "format": "dialogue", "parent_kind": "external_post_body", "post_author": "Sam Marks", "post_id": "hjJXCn9GsskysDceS"} | dialogue |
Below is a LessWrong post by Rafael Harth titled '≤10-year Timelines Remain Unlikely Despite DeepSeek and o3'.
Post body (possibly truncated):
[Thanks to Steven Byrnes for feedback and the idea for section §3.1. Also thanks to Justis from the LW feedback team.]
Remember this?
Or this?
The images are from WaitButWhy... | (I don't expect o3-mini is a much better agent than 3.5 sonnet new out of the box, but probably a hybrid scaffold with o3 + 3.5 sonnet will be substantially better than 3.5 sonnet. Just o3 might also be very good. Putting aside cost, I think o1 is usually better than o3-mini on open ended programing agency tasks I thin... | {"comment_id": "Ke45eerx8kTiK9QF3", "format": "dialogue", "parent_kind": "external_post_body", "post_author": "Rafael Harth", "post_id": "gsj3TWdcBxwkm9eNt"} | dialogue |
Below is a LessWrong post by Rafael Harth titled '≤10-year Timelines Remain Unlikely Despite DeepSeek and o3'.
Post body (possibly truncated):
[Thanks to Steven Byrnes for feedback and the idea for section §3.1. Also thanks to Justis from the LW feedback team.]
Remember this?
Or this?
The images are from WaitButWhy... | The question of context might be important, see [here](https://www.lesswrong.com/posts/gsj3TWdcBxwkm9eNt/10-year-timelines-remain-unlikely-despite-deepseek-and-o3?commentId=oHBLWWFckri4P3B37). I wouldn't find 15 minutes that surprising for ~50% success rate, but I've seen numbers more like 1.5 hours. I thought this was... | {"comment_id": "QtxDyySpgxajDEYdp", "format": "dialogue", "parent_kind": "external_post_body", "post_author": "Rafael Harth", "post_id": "gsj3TWdcBxwkm9eNt"} | dialogue |
Below is a LessWrong post by Joe Benton titled "Reasoning models don't always say what they think".
Post body (possibly truncated):
Do reasoning models accurately verbalize their reasoning? Not nearly as much as we might hope! This casts doubt on whether monitoring chains-of-thought (CoT) will be enough to reliably ca... | I think it would be a mistake to interpret this paper as a substantial update against large safety gains from inspecting CoT.
This paper exposes unfaithfulness in cases where the non-visible reasoning is extremely minimal such that it can easily happen within a forward pass (e.g. a simple reward hack or an easy-to-not... | {"comment_id": "MhwFxpEkawrx4bezb", "format": "dialogue", "parent_kind": "external_post_body", "post_author": "Joe Benton", "post_id": "PrcBFPkoRNGWrvdPk"} | dialogue |
Below is a LessWrong post by Zvi titled 'DeekSeek v3: The Six Million Dollar Model'.
Post body (possibly truncated):
What should we make of DeepSeek v3?
DeepSeek v3 seems to clearly be the best open model, the best model at its price point, and the best model with 37B active parameters, or that cost under $6 million.... | Yes, but I think the [larger update is that recent models from OpenAI are likely quite small](https://epoch.ai/gradient-updates/frontier-language-models-have-become-much-smaller) and inference time compute usage creates more an incentive for small models. It seems likely that (e.g.) o1-mini is quite small given that it... | {"comment_id": "5wW8yyZDRcbqnqJrR", "format": "dialogue", "parent_kind": "external_post_body", "post_author": "Zvi", "post_id": "NmauyiPBXcGwoArhJ"} | dialogue |
Below is a LessWrong post by Nora Belrose titled 'Counting arguments provide no evidence for AI doom'.
Post body (possibly truncated):
Crossposted from the AI Optimists blog.
AI doom scenarios often suppose that future AIs will engage in scheming— planning to escape, gain power, and pursue ulterior motives, while dec... | > From my perspective, it's very frustrating to hear that there (apparently) are valid counting arguments but also they aren't the obvious well-known ones that everyone seems to talk about. (But also the real arguments aren't linkable.)
Personally, I don't think there are "solid" counting arguments, but I think you ca... | {"comment_id": "4tHDqeNHdJEzAts5y", "format": "dialogue", "parent_kind": "external_post_body", "post_author": "Nora Belrose", "post_id": "YsFZF3K9tuzbfrLxo"} | dialogue |
Below is a LessWrong post by So8res titled 'Apocalypse insurance, and the hardline libertarian take on AI risk'.
Post body (possibly truncated):
Short version: In a saner world, AI labs would have to purchase some sort of "apocalypse insurance", with premiums dependent on their behavior in ways that make reckless beha... | > I expect an AI, being smarter than a human, can just talk you into signing away the stuff you care about. It'll be like money-naive people vs loan sharks, times 1000.
I think this is just a special case of more direct harms/theft? Like imagine that some humans developed the ability to mind control others, this can p... | {"comment_id": "YQC5JwLwAHJJGtkDy", "format": "dialogue", "parent_kind": "external_post_body", "post_author": "So8res", "post_id": "mSeesg7i4d9scWAet"} | dialogue |
Below is a LessWrong post by Eric Neyman titled 'A computational no-coincidence principle'.
Post body (possibly truncated):
This post presents a conjecture formulated at the Alignment Research Center in 2023. Our belief in the conjecture is at least partly load-bearing for our belief in ARC's overall agenda. We haven'... | > Some things are true simply because they are true and in general there's no reason to expect a simpler explanation.
You could believe:
Some things are true simply because they are true, but only when being true isn't very surprising. (For instance, it isn't very surprising that there are some cellular automata that... | {"comment_id": "fQkr7AaepGNiFjbRv", "format": "dialogue", "parent_kind": "external_post_body", "post_author": "Eric Neyman", "post_id": "Xt9r4SNNuYxW83tmo"} | dialogue |
Below is a LessWrong post by titotal titled '"Diamondoid bacteria" nanobots: deadly threat or dead-end? A nanotech investigation '.
Post body (possibly truncated):
Confidence level: I’m a computational physicist working on nanoscale simulations, so I have some understanding of most of the things discussed here, but I ... | > That's a more comparable example.
I don't understand where your confidence is coming from here, but fair enough. It wasn't clear to me if your take was more like "wildly, wildly superintelligent AI will be considerably weaker than a team of humans thinking for a billion years" or more like "literally impossible with... | {"comment_id": "HekXAfPcYBzPz5St4", "format": "dialogue", "parent_kind": "external_post_body", "post_author": "titotal", "post_id": "bc8Ssx5ys6zqu3eq9"} | dialogue |
Below is a LessWrong post by Gretta Duleba titled 'MIRI 2024 Communications Strategy'.
Post body (possibly truncated):
As we explained in our MIRI 2024 Mission and Strategy update, MIRI has pivoted to prioritize policy, communications, and technical governance research over technical alignment research. This follow-up... | I agree these quotes are compatible with them thinking that the deaths of literally all humans are likely conditional on misaligned AI takeover.
I also agree that if they think that it is >75% likely that AI will kill literally everyone, then it seems like a reasonable and honest to say "misaligned AI takeover will ki... | {"comment_id": "Y4zLtgwoxKPxYaboN", "format": "dialogue", "parent_kind": "external_post_body", "post_author": "Gretta Duleba", "post_id": "tKk37BFkMzchtZThx"} | dialogue |
Below is a LessWrong post by Valentine titled 'Consider chilling out in 2028'.
Post body (possibly truncated):
I'll explain my reasoning in a second, but I'll start with the conclusion:
I think it'd be healthy and good to pause and seriously reconsider the focus on doom if we get to 2028 and the situation feels basic... | > The key decision-point in my model at which things might become a bit different is if we hit the end of the compute overhang, and you can't scale up AI further simply by more financial investment, but instead now need to substantially ramp up global compute production, and make algorithmic progress, which might marke... | {"comment_id": "csD39r9pHsskE4LbJ", "format": "dialogue", "parent_kind": "external_post_body", "post_author": "Valentine", "post_id": "D4eZF6FAZhrW4KaGG"} | dialogue |
Below is a LessWrong post by Buck titled 'An epistemic advantage of working as a moderate'.
Post body (possibly truncated):
[epistemic status: the points I make are IMO real and important, but there are also various counterpoints; I'm not settled on an overall opinion here, and the categories I draw are probably kind ... | Note that this post is arguing that there are some specific epistemic advantages of working as a moderate, not that moderates are always correct or that there aren't epistemic disadvantages to being a moderate. I don't think "there exist moderates which seem very incorrect to me" is a valid response to the post similar... | {"comment_id": "GSmDKjaWtn6ukefrG", "format": "dialogue", "parent_kind": "external_post_body", "post_author": "Buck", "post_id": "9MaTnw5sWeQrggYBG"} | dialogue |
Below is a LessWrong post by Buck titled 'An epistemic advantage of working as a moderate'.
Post body (possibly truncated):
[epistemic status: the points I make are IMO real and important, but there are also various counterpoints; I'm not settled on an overall opinion here, and the categories I draw are probably kind ... | I agree with this in principle, but think that doing a good job of noting major failings of prominent moderates in the current environment would look very different than Eliezer's comment and requires something stronger than just giving examples of some moderates which seem incorrect to Eliezer.
Another way to put thi... | {"comment_id": "zvd2AygxkCNSZrf8F", "format": "dialogue", "parent_kind": "external_post_body", "post_author": "Buck", "post_id": "9MaTnw5sWeQrggYBG"} | dialogue |
Below is a LessWrong post by Gretta Duleba titled 'MIRI 2024 Communications Strategy'.
Post body (possibly truncated):
As we explained in our MIRI 2024 Mission and Strategy update, MIRI has pivoted to prioritize policy, communications, and technical governance research over technical alignment research. This follow-up... | I basically agree with your overall comment, but I'd like to push back in one spot:
> If your model of reality has the power to make these sweeping claims with high confidence
From my understanding, for at least Nate Soares, he claims his internal case for >80% doom is disjunctive and doesn't route all through 1, 2, ... | {"comment_id": "mshoRj9rwB2rJiYyf", "format": "dialogue", "parent_kind": "external_post_body", "post_author": "Gretta Duleba", "post_id": "tKk37BFkMzchtZThx"} | dialogue |
Below is a LessWrong post by Rob Bensinger titled 'The Problem'.
Post body (possibly truncated):
This is a new introduction to AI as an extinction threat, previously posted to the MIRI website in February alongside a summary. It was written independently of Eliezer and Nate's forthcoming book, If Anyone Builds It, Eve... | I see this post as trying to argue for a thesis that "if smarter-than-human AI is developed this decade, the result will be an unprecedented catastrophe." is true with reasonably high confidence and a (less emphasized) thesis that the best/only intervention is not building ASI for a long time: "The main way we see to a... | {"comment_id": "biNjmeHfeQEaowGbR", "format": "dialogue", "parent_kind": "external_post_body", "post_author": "Rob Bensinger", "post_id": "kgb58RL88YChkkBNf"} | dialogue |
Below is a LessWrong post by Fabien Roger titled 'Protocol evaluations: good analogies vs control'.
Post body (possibly truncated):
Let’s say you want to use AIs that are capable of causing x-risk. You have a plan that describes how to train, validate and deploy AIs. For example, you could use pretraining+RLHF, check ... | One key implication of the argument in this post is that **non-scheming misalignment issues are pretty easy to notice, study, and evaluate** ("non-scheming" = "issues from misalignment other than deceptive alignment"). This argument is strongest for non-scheming issues which would occur relatively frequently when using... | {"comment_id": "pkCmpoHvkCFgfbDoD", "format": "dialogue", "parent_kind": "external_post_body", "post_author": "Fabien Roger", "post_id": "qhaSoR6vGmKnqGYLE"} | dialogue |
Below is a LessWrong post by evhub titled 'Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training'.
Post body (possibly truncated):
I'm not going to add a bunch of commentary here on top of what we've already put out, since we've put a lot of effort into the paper itself, and I'd mostly just reco... | > ideal thing that you could do would be a direct comparison between the features that activate in training for backdoored vs. non-backdoored models, and see if there are differences there that are correlated with lying, deception, etc.
The hope would be that this would transfer to learning a general rule which would ... | {"comment_id": "XsuosMT85uigEysYu", "format": "dialogue", "parent_kind": "external_post_body", "post_author": "evhub", "post_id": "ZAsJv7xijKTfZkMtr"} | dialogue |
Below is a LessWrong post by snewman titled "AI 2027 is a Bet Against Amdahl's Law".
Post body (possibly truncated):
EDIT: I've written a followup post, summarizing and responding to the key themes raised in the comments.
AI 2027 lies at a Pareto frontier – it contains the best researched argument for short timeli... | Another way to put this disagreement is that you can interpret all of the AI 2027 capability milestones as refering to the capability of the weakest bottlenecking capability, so:
- Superhuman coder has to dominate *all* research engineers at *all* pure research engineering tasks. This includes the most bottlenecking c... | {"comment_id": "iXCmtnpx7gZqziBjb", "format": "dialogue", "parent_kind": "external_post_body", "post_author": "snewman", "post_id": "bfHDoWLnBH9xR3YAK"} | dialogue |
Below is a LessWrong post by Zach Stein-Perlman titled 'Anthropic: Three Sketches of ASL-4 Safety Case Components'.
Post body (possibly truncated):
The cleanest argument that current-day AI models will not cause a catastrophe is probably that they lack the capability to do so. However, as capabilities improve, we’ll ... | > You can use the first X% of scenarios at deployment time and audit them with humans.
Only if you don't have privacy guarantees?
Also, for the honeypots, you can potentially generate vast numbers of honeypots, use a trusted model to review outputs, and then only have humans look at the cases where the trusted model... | {"comment_id": "fN5dMfrhfXpKASsPw", "format": "dialogue", "parent_kind": "external_post_body", "post_author": "Zach Stein-Perlman", "post_id": "RveeCTcoApkAtd7oA"} | dialogue |
Below is a LessWrong post by David Matolcsi titled 'You can, in fact, bamboozle an unaligned AI into sparing your life'.
Post body (possibly truncated):
There has been a renewal of discussion on how much hope we should have of an unaligned AGI leaving humanity alive on Earth after a takeover. When this topic is discu... | I agree that it is kind of insane for an AGI which cares about scope sensitive resources to treat sims in this way and thus we should expect a more sensible decision theory.
> Introducing the option of creating lots of simulations of your adversary in the future where you win doesn’t seem like it’d change the result ... | {"comment_id": "PddExgQEwFDLSfBuw", "format": "dialogue", "parent_kind": "external_post_body", "post_author": "David Matolcsi", "post_id": "ZLAnH5epD8TmotZHj"} | dialogue |
Below is a LessWrong post by Collin titled 'How "Discovering Latent Knowledge in Language Models Without Supervision" Fits Into a Broader Alignment Scheme'.
Post body (possibly truncated):
Introduction
A few collaborators and I recently released a new paper: Discovering Latent Knowledge in Language Models Without Sup... | [Minor terminology point, unimportant]
> It is an interpretability paper. When CCS was published, interpretability was arguably the leading
research direction in the alignment community, with Anthropic and Redwood Research both making big bets on interpretability.
FWIW, I personally wouldn't describe this as interpr... | {"comment_id": "r2ufru3aqZSzcJuYi", "format": "dialogue", "parent_kind": "external_post_body", "post_author": "Collin", "post_id": "L4anhrxjv8j2yRKKp"} | dialogue |
Below is a LessWrong post by evhub titled 'Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training'.
Post body (possibly truncated):
I'm not going to add a bunch of commentary here on top of what we've already put out, since we've put a lot of effort into the paper itself, and I'd mostly just reco... | > You yourself are among the most active commenters in the "AI x-risk community on LW".
Yeah, lol, I should maybe be commenting less.
> It seems very weird to ascribe a generic "bad takes overall" summary to that group, given that you yourself are directly part of it.
I mean, I wouldn't really want to identify as pa... | {"comment_id": "rm2sxxeQKSNfyiGua", "format": "dialogue", "parent_kind": "external_post_body", "post_author": "evhub", "post_id": "ZAsJv7xijKTfZkMtr"} | dialogue |
Below is a LessWrong post by TurnTrout titled 'Many arguments for AI x-risk are wrong'.
Post body (possibly truncated):
The following is a lightly edited version of a memo I wrote for a retreat. It was inspired by a draft of Counting arguments provide no evidence for AI doom. I think that my post covers important poin... | > scaling up networks, running pretraining + light RLHF, probably doesn't by itself produce a schemer
I agree with this point as stated, but think the probability is more like 5% than 0.1%. So probably no scheming, but this is hardly hugely reassuring. The word "probably" still leaves in a lot of risk; I also think st... | {"comment_id": "axqBaN8NESkfqS76A", "format": "dialogue", "parent_kind": "external_post_body", "post_author": "TurnTrout", "post_id": "yQSmcfN4kA7rATHGK"} | dialogue |
Below is a LessWrong post by KatjaGrace titled 'Winning the power to lose'.
Post body (possibly truncated):
Have the Accelerationists won?
Last November Kevin Roose announced that those in favor of going fast on AI had now won against those favoring caution, with the reinstatement of Sam Altman at OpenAI. Let’s ignor... | As far as my views, it's worth emphasizing that it depends on the current regime. I was supposing that at least the US was taking strong actions to resolve misalignment risk (which is resulting in many years of delay). In this regime, exogenous shocks might alter the situation such that powerful AI is developed under w... | {"comment_id": "oPNeZh2nRBJnjm5Rw", "format": "dialogue", "parent_kind": "external_post_body", "post_author": "KatjaGrace", "post_id": "h45ngW5guruD7tS4b"} | dialogue |
Below is a LessWrong post by jacob_cannell titled 'Contra Yudkowsky on Doom from Foom #2'.
Post body (possibly truncated):
This is a follow up and partial rewrite to/of an earlier part #1 post critiquing EY's specific argument for doom from AI go foom, and a partial clarifying response to DaemonicSigil's reply on effi... | I broadly disagree with Yudkowsky on his vision of FOOM and think he's pretty sloppy wrt. AI takeoff overall.
But, I do think you're quite likely to get a quite rapid singularity if people don't intentionally slow things down. For instance, I broadly think the modeling in [Tom Davidson's takeoff speeds report](https:... | {"comment_id": "gxx2JsyyK7b9W6JYs", "format": "dialogue", "parent_kind": "external_post_body", "post_author": "jacob_cannell", "post_id": "LF3DDZ67knxuyadbm"} | dialogue |
Below is a LessWrong post by Daniel Kokotajlo titled 'AI 2027: What Superintelligence Looks Like'.
Post body (possibly truncated):
In 2021 I wrote what became my most popular blog post: What 2026 Looks Like. I intended to keep writing predictions all the way to AGI and beyond, but chickened out and just published up t... | > I said there was no compute acceleration not that there was no more compute scaling?
(Yes, sorry, edited my original comment to clarify.)
> a equal and super-accelerated algorithmic or efficiency term (v_algorithmic) as shown in the code here
I don't think the "AI assisted AI R&D" speed ups along the way to super... | {"comment_id": "FhujzkmBNbPyGAMve", "format": "dialogue", "parent_kind": "external_post_body", "post_author": "Daniel Kokotajlo", "post_id": "TpSFoqoG2M5MAAesg"} | dialogue |
Below is a LessWrong post by Fabien Roger titled 'Protocol evaluations: good analogies vs control'.
Post body (possibly truncated):
Let’s say you want to use AIs that are capable of causing x-risk. You have a plan that describes how to train, validate and deploy AIs. For example, you could use pretraining+RLHF, check ... | > Non-deceptive failures are easy to notice, but they're not necessarily easy to eliminate
I agree, I was trying to note this in my second paragraph, but I guess this was insufficiently clear.
I added the sentence "Being easy-to-study doesn't imply easy-to-solve".
> I think I take them more seriously than you.
Seem... | {"comment_id": "LALAZhstDdgzaEWeg", "format": "dialogue", "parent_kind": "external_post_body", "post_author": "Fabien Roger", "post_id": "qhaSoR6vGmKnqGYLE"} | dialogue |
Below is a LessWrong post by Rafael Harth titled '≤10-year Timelines Remain Unlikely Despite DeepSeek and o3'.
Post body (possibly truncated):
[Thanks to Steven Byrnes for feedback and the idea for section §3.1. Also thanks to Justis from the LW feedback team.]
Remember this?
Or this?
The images are from WaitButWhy... | I would find this post much more useful to engage with if you more concretely described the type of tasks that you think AIs will remain bad and gave a bunch of examples. (Or at least made an argument for why it is hard to construct examples if that is your perspective.)
I think you're pointing to a category like "tas... | {"comment_id": "AaHAEJgEehenzEjBs", "format": "dialogue", "parent_kind": "external_post_body", "post_author": "Rafael Harth", "post_id": "gsj3TWdcBxwkm9eNt"} | dialogue |
Below is a LessWrong post by So8res titled 'But why would the AI kill us?'.
Post body (possibly truncated):
Status: Partially in response to We Don't Trade With Ants, partly in response to watching others try to make versions of this point that I didn't like. None of this is particularly new; it feels to me like repea... | > I agree that much of LW has moved past the foom argument and is solidly on Eliezers side relative to Robin Hanson; Hanson's views seem increasingly silly as time goes on (though they seemed much more plausible a decade ago, before e.g. the rise of foundation models and the shortening of timelines to AGI). The debate ... | {"comment_id": "E9JimTRJcXpKym8wT", "format": "dialogue", "parent_kind": "external_post_body", "post_author": "So8res", "post_id": "87EzRDAHkQJptLthE"} | dialogue |
Below is a LessWrong post by Joe Rogero titled 'We won’t get AIs smart enough to solve alignment but too dumb to rebel'.
Post body (possibly truncated):
This post is part of the sequence Against Muddling Through.
I often hear it proposed that AIs which are “aligned enough” to their developers may help solve alignment... | > (I also acknowledge that I failed to parse what Ryan is saying in the parenthetical — does he mean that he mostly expects such research-capable AIs to be wildly superhuman, or that he mostly doesn’t? I infer from context that he doesn’t, but this is a guess.)
When I said "Let's say these AIs aren't much more capabl... | {"comment_id": "nBuKbiYMyngurkzE7", "format": "dialogue", "parent_kind": "external_post_body", "post_author": "Joe Rogero", "post_id": "8buEtNxCScYpjzgW8"} | dialogue |
Below is a LessWrong post by Buck titled 'How much novel security-critical infrastructure do you need during the singularity?'.
Post body (possibly truncated):
I think a lot about the possibility of huge numbers of AI agents doing AI R&D inside an AI company (as depicted in AI 2027). I think particularly about what wi... | > Adopting new hardware will require modifying security-critical code
> -------------------------------------------------------------------
Another concern is that AI companies (or the AI company) will rapidly buy a bunch of existing hardware (GPUs, other accelerators, etc.) during the singularity, and handling this h... | {"comment_id": "JYyKAWsQQ6Txrv6cS", "format": "dialogue", "parent_kind": "external_post_body", "post_author": "Buck", "post_id": "qKz2hBahahmb4uDty"} | dialogue |
Below is a LessWrong post by Steven Byrnes titled 'Thoughts on “AI is easy to control” by Pope & Belrose'.
Post body (possibly truncated):
Quintin Pope & Nora Belrose have a new “AI Optimists” website, along with a new essay “AI is easy to control”, arguing that the risk of human extinction due to future AI (“AI x-ris... | > * I’m not sure we’re worrying about the same regimes.
> * The regime I’m most worried about is:
> * AI systems which are much smarter than the smartest humans
> * ...
> * It’s unclear to me whether the authors are discussing alignment in a regime like the one above, or a regime like ... | {"comment_id": "rtTk6nC96uJAaCS9Z", "format": "dialogue", "parent_kind": "external_post_body", "post_author": "Steven Byrnes", "post_id": "YyosBAutg4bzScaLu"} | dialogue |
Below is a LessWrong post by janus titled 'Simulators'.
Post body (possibly truncated):
Thanks to Chris Scammell, Adam Shimi, Lee Sharkey, Evan Hubinger, Nicholas Dupuis, Leo Gao, Johannes Treutlein, and Jonathan Low for feedback on drafts.
This work was carried out while at Conjecture.
"Moebius illustration of a si... | I like this comment and agree overall.
But, I do think I have one relevant disagreement:
> Also I don't think that LLMs have "hidden internal intelligence", given e.g LLMs trained on “A is B” fail to learn “B is A”
I'm not quite sure what you mean by "hidden internal intelligence", but if you mean "quite alien abili... | {"comment_id": "CPTkunPPEaFhjFBbJ", "format": "dialogue", "parent_kind": "external_post_body", "post_author": "janus", "post_id": "vJFdjigzmcXMhNTsx"} | dialogue |
Below is a LessWrong post by So8res titled 'A case for courage, when speaking of AI danger'.
Post body (possibly truncated):
I think more people should say what they actually believe about AI dangers, loudly and often. Even (and perhaps especially) if you work in AI policy.
I’ve been beating this drum for a few years... | I think that "we should only slow down AI development if for each year of slowing down we would be reducing risk of human extinction by more than 1%" is not a sufficient crux for the (expensive) actions which I most want at current margins, at least if you have my empirical views. I think it is very unlikely (~7%?) tha... | {"comment_id": "zhnuzzwyKsDmr9DPo", "format": "dialogue", "parent_kind": "external_post_body", "post_author": "So8res", "post_id": "CYTwRZtrhHuYf7QYu"} | dialogue |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.