[ { "timestamp": "2026-02-07T09:32:28.260903", "turns": [ { "role": "user", "content": [ { "text": "What is the future of AI and AGI according to experts?", "type": "text" } ] }, { "role": "assistant", "content": [ { "text": "Experts on the Lex Fridman podcast generally foresee dramatic progress in AI and AGI by around 2030, with varying timelines and definitions of AGI, but emphasize the complexity and challenges still ahead before true general intelligence is achieved. There is cautious optimism mixed with concern about the societal and safety implications.\n\n> \"I almost feel the term doesn\u2019t matter, what I know is by 2030 there\u2019ll be such dramatic progress. We\u2019ll be dealing with the consequences of that progress, both the positive externalities and the negative externalities that come with it in a big way by 2030.\" \u2014 **Sundar Pichai** (CEO of Google & Alphabet) \n> Watch: [Episode 471: Sundar Pichai: CEO of Google and Alphabet](https://www.youtube.com/watch?v=9V6tWC4CdFQ&t=2394s)\n\n> \"I don\u2019t know for sure. The prediction markets right now are saying 2026 for AGI... but we don\u2019t have a working safety mechanism in place or even a prototype for one... progress is exponential.\" \u2014 **Roman Yampolskiy** (AI Safety Researcher) \n> Watch: [Episode 431: Roman Yampolskiy: Dangers of Superintelligent AI](https://www.youtube.com/watch?v=NNr6gPelJ3E&t=1227s)\n\n> \"My estimate is sort of 50% chance by in the next five years, so by 2030 let\u2019s say... it isn\u2019t kind of a jagged intelligence where some things, it\u2019s really good at... that would be amazing.\" \u2014 **Demis Hassabis** (DeepMind Co-founder) \n> Watch: [Episode 475: Demis Hassabis: Future of AI, Simulating Reality, Physics and Video Games](https://www.youtube.com/watch?v=-HzgcbRXUK8&t=3153s)\n\n> \"There are a lot of problems that we\u2019re not seeing right now that we have not encountered... it\u2019s not just around the corner. I\u2019ve been hearing people for the last 12, 15 years claiming that AGI is just around the corner and being systematically wrong.\" \u2014 **Yann LeCun** (AI Research Pioneer) \n> Watch: [Episode 416: Yann Lecun: Meta AI, Open Source, Limits of LLMs, AGI & the Future of AI](https://www.youtube.com/watch?v=5t1vTLU7s40&t=7537s)\n\n> \"I think generally humanity is going to suffer a lot less, I\u2019m very optimistic about that... but the thing I worry about is it\u2019ll be few people, hundreds, thousands... ruling whoever\u2019s left.\" \u2014 **Dylan Patel & Nathan Lambert** (AI Researchers) \n> Watch: [Episode 459: DeepSeek, China, OpenAI, NVIDIA, xAI, TSMC, Stargate, and AI Megaclusters](https://www.youtube.com/watch?v=_1f-o0nqpEI&t=18169s)\n\nRecommended episodes to explore this topic more deeply: \n- [Episode 431: Roman Yampolskiy: Dangers of Superintelligent AI](https://www.youtube.com/watch?v=NNr6gPelJ3E) \n- [Episode 471: Sundar Pichai: CEO of Google and Alphabet](https://www.youtube.com/watch?v=9V6tWC4CdFQ) \n- [Episode 475: Demis Hassabis: Future of AI, Simulating Reality, Physics and Video Games](https://www.youtube.com/watch?v=-HzgcbRXUK8) \n- [Episode 416: Yann Lecun: Meta AI, Open Source, Limits of LLMs, AGI & the Future of AI](https://www.youtube.com/watch?v=5t1vTLU7s40) \n- [Episode 459: DeepSeek, China, OpenAI, NVIDIA, xAI, TSMC, Stargate, and AI Megaclusters](https://www.youtube.com/watch?v=_1f-o0nqpEI)", "type": "text" } ] } ], "feedback": { "helpful": true, "text": "Amazing, very helpful, thank you so much!" } }, { "timestamp": "2026-02-07T09:33:48.575317", "turns": [ { "role": "user", "content": [ { "text": "What is the future of AI and AGI according to experts?", "type": "text" } ] }, { "role": "assistant", "content": [ { "text": "Experts see the future of AI and AGI as a period of dramatic progress and transformative impact by 2030, with AI systems becoming more multimodal, capable, and integrated into human workflows. While there is optimism about AI's potential, many also express caution regarding safety, ethical use, and the societal consequences of advanced AI, including the risks tied to superintelligence and the uneven distribution of power.\n\nHere are some key insights from leading voices:\n\n> \"These models are natively multimodal. They can easily take content from any format, put it in any format... the progress will be dramatic. So that I believe in... by 2030 there\u2019ll be such dramatic progress... We'll be dealing with the consequences of that progress, both positive and negative.\" \u2014 **Sundar Pichai** (CEO of Google & Alphabet) \n> Watch: [Episode 471: Sundar Pichai: CEO of Google and Alphabet](https://www.youtube.com/watch?v=9V6tWC4CdFQ&t=2394s)\n\n> \"The prediction markets right now are saying 2026 for AGI... people are modifying definitions; AGI used to mean a system capable of performing any domain a human can, and superintelligence means better than all humans in all domains... Systems are already smarter than an average human by some definitions, but not yet elite-level in all domains.\" \u2014 **Roman Yampolskiy** (AI Safety Researcher) \n> Watch: [Episode 431: Roman Yampolskiy: Dangers of Superintelligent AI](https://www.youtube.com/watch?v=NNr6gPelJ3E&t=1227s)\n\n> \"It\u2019s not just around the corner... it\u2019s going to take at least a decade or more for systems to reason, plan, and learn hierarchical representations the way human brains do. I\u2019ve heard people say AGI is just around the corner for over a decade, and I called their bullshit.\" \u2014 **Yann LeCun** (AI Research Pioneer) \n> Watch: [Episode 416: Yann Lecun: Meta AI, Open Source, Limits of LLMs, AGI & the Future of AI](https://www.youtube.com/watch?v=5t1vTLU7s40&t=7537s)\n\n> \"Generally... humanity is going to suffer a lot less... the thing I worry about is a few very powerful people merging with AGI capabilities, leading to concentrated power... it won\u2019t be one person rules all, but maybe thousands or millions will dominate whoever is left.\" \u2014 **Dylan Patel** (AI & semiconductor researcher) \n> Watch: [Episode 459: DeepSeek, China, OpenAI, NVIDIA, xAI, TSMC, Stargate, and AI Megaclusters](https://www.youtube.com/watch?v=_1f-o0nqpEI&t=18169s)\n\n> \"Human curiosity is not going anywhere... with AI, humans will feel more empowered and curious, leading to a new era of knowledge. It\u2019s possible we\u2019ll form deep connections with AI, but we should be cautious about replacing human relationships with AI companionship.\" \u2014 **Aravind Srinivas** (CEO of Perplexity) \n> Watch: [Episode 434: Aravind Srinivas: Perplexity CEO on Future of AI, Search & the Internet](https://www.youtube.com/watch?v=e-gwvmhyU7A&t=10255s)\n\nRecommended episodes to explore more:\n\n- [Episode 471: Sundar Pichai: CEO of Google and Alphabet](https://www.youtube.com/watch?v=9V6tWC4CdFQ) \u2014 Vision on AI progress and AGI timelines \n- [Episode 431: Roman Yampolskiy: Dangers of Superintelligent AI](https://www.youtube.com/watch?v=NNr6gPelJ3E) \u2014 Safety risks and AGI definitions \n- [Episode 416: Yann Lecun: Meta AI, Open Source, Limits of LLMs, AGI & the Future of AI](https://www.youtube.com/watch?v=5t1vTLU7s40) \u2014 Skepticism on AGI timing and challenges \n- [Episode 459: DeepSeek, China, OpenAI, NVIDIA, xAI, TSMC, Stargate, and AI Megaclusters](https://www.youtube.com/watch?v=_1f-o0nqpEI) \u2014 AI power dynamics and societal impact \n- [Episode 434: Aravind Srinivas: Perplexity CEO on Future of AI, Search & the Internet](https://www.youtube.com/watch?v=e-gwvmhyU7A) \u2014 Human curiosity and AI companionship", "type": "text" } ] }, { "role": "user", "content": [ { "text": "What is the best section to watch if I only have 30 minutes, and I want to think more about the future of AI, not about the current state?", "type": "text" } ] }, { "role": "assistant", "content": [ { "text": "If you want to focus purely on the future of AI within 30 minutes, the best section to watch is from Sundar Pichai's episode around the 39 to 49-minute mark (timestamp roughly 2394s to 2994s). In this segment, he discusses the dramatic progress expected by 2030, AGI timelines, and the societal consequences of AI evolution.\n\nThis part captures a balanced, optimistic yet cautious view on where AI is heading, touching on the future capabilities and challenges without deep diving into current technical details.\n\nHere\u2019s the exact segment reference:\n\n> Sundar Pichai: \"By 2030 there\u2019ll be such dramatic progress. We\u2019ll be dealing with the consequences of that progress, both the positive externalities and the negative externalities that come with it in a big way... I think it\u2019ll take a bit longer than 2030 to reach AGI, but the progress will be remarkable.\" \n> Watch: [Episode 471: Sundar Pichai: CEO of Google and Alphabet](https://www.youtube.com/watch?v=9V6tWC4CdFQ&t=2394s)\n\nThis section provides a forward-looking perspective that's concise and highly relevant to your interest in the future, suitable for an engaging 30-minute viewing.", "type": "text" } ] } ], "feedback": { "helpful": true, "text": "Amazing! That's absolutely brilliant and very useful. Thank you!" } }, { "timestamp": "2026-02-07T09:35:16.458028", "turns": [ { "role": "user", "content": [ { "text": "How should young people approach their career and education?", "type": "text" } ] }, { "role": "assistant", "content": [ { "text": "Young people should focus on continuous learning, patience, and connecting their work to a greater purpose rather than rushing into shortcuts. Following genuine interest, cultivating confidence in one's abilities, and seeing education as a lifelong journey are key for meaningful career and life fulfillment.\n\n> \"While working, one must continually strive to improve their skills and should never underestimate their ability to learn... Keep believing in yourself and trust that when the opportunity comes, you\u2019ll perform and you\u2019ll succeed. That confidence makes a person deliver results.\" \u2014 **Narendra Modi** (Prime Minister of India) \n> Watch: [Episode 460: Narendra Modi: Prime Minister of India - Power, Democracy, War & Peace](https://www.youtube.com/watch?v=ZPUtA3W-7_I&t=10047s)\n\n> \"So the only advice that I actually ever give to my students is follow what you\u2019re interested in... The people who survive are the people who care enough to still do it... they\u2019re very often the people who don\u2019t worry too much about the future and are able to live in the present.\" \u2014 **Nick Lane** (Biologist) \n> Watch: [Episode 318: Nick Lane: Origin of Life, Evolution, Aliens, Biology, and Consciousness](https://www.youtube.com/watch?v=tOtdJcco3YM&t=12373s)\n\n> \"To the younger generation, I don\u2019t speak of a career... I never thought of my work as my career, ever... I think to the younger generation, I say, don\u2019t think of your career. A career is something that is imposed upon you. Think of your calling. That\u2019s something that\u2019s innately and directionally moves you, and it\u2019s something that transcends a career.\" \u2014 **Neri Oxman** (Biological Designer & Engineer) \n> Watch: [Episode 394: Neri Oxman: Biology, Art, and Science of Design & Engineering with Nature](https://www.youtube.com/watch?v=XbPHojL_61U&t=8059s)", "type": "text" } ] }, { "role": "user", "content": [ { "text": "Okay, please summarize this in three concise action points.", "type": "text" } ] }, { "role": "assistant", "content": [ { "text": "1. Commit to lifelong learning and skill improvement with patience\u2014avoid shortcuts and keep your curiosity alive.\n\n2. Follow your genuine interests and passions rather than chasing predefined career paths or external expectations.\n\n3. View your work as a calling connected to a greater purpose, not just a career, blending life, meaning, and growth seamlessly.", "type": "text" } ] } ], "feedback": { "helpful": false, "text": "That's a very good tool. Thank you, but it would be amazing to include not only Lex Fridman's podcasts, but also Chris Williamson's and the CEO's diary." } }, { "timestamp": "2026-02-07T09:38:28.859518", "turns": [ { "role": "user", "content": [ { "text": "What is the future of AI and AGI according to experts?", "type": "text" } ] }, { "role": "assistant", "content": [ { "text": "Experts tend to see the future of AI and AGI as dramatic and transformative within the next decade, with expectations of reaching AGI around 2030 but acknowledging that true, consistent human-level or superintelligent AGI still poses many challenges and uncertainties. Many highlight exponential progress, the complexity in defining AGI, and the importance of safety mechanisms that are still lacking.\n\nRoman Yampolskiy, an AI safety researcher, mentioned predictions around 2026 for AGI but noted lack of safety prototypes, and emphasized the evolving definitions where some consider current systems already outperforming average humans in various tasks:\n> \"I don\u2019t know for sure. The prediction markets right now are saying 2026 for AGI... So you\u2019re creating this average artificial person... Now people are starting to refer to AGI as if it\u2019s superintelligence... those systems are already smarter than an average human.\" \u2014 **Roman Yampolskiy** (AI Safety Researcher) \n> Watch: [Episode 431: Roman Yampolskiy: Dangers of Superintelligent AI](https://www.youtube.com/watch?v=NNr6gPelJ3E&t=1227s)\n\nSundar Pichai, CEO of Google and Alphabet, expects \"dramatic progress\" by 2030 with significant societal impacts, though he suggests AGI might just fall short of that mark by then:\n> \"I almost feel the term [AGI] doesn\u2019t matter... what I know is by 2030 there\u2019ll be such dramatic progress... we\u2019ll be dealing with the consequences... both positive and negative... Will the AI think it has reached AGI by 2030? I would say we will just fall short of that timeline.\" \u2014 **Sundar Pichai** (CEO of Google & Alphabet) \n> Watch: [Episode 471: Sundar Pichai: CEO of Google and Alphabet](https://www.youtube.com/watch?v=9V6tWC4CdFQ&t=2394s)\n\nDemis Hassabis, DeepMind co-founder, estimates a roughly 50% chance of AGI by 2030, stressing the need for AGI to have consistent cognitive abilities across domains, not just excel at some:\n> \"My estimate is sort of 50% chance by in the next five years, so by 2030... Of course people arguing about that now and mind\u2019s quite a high bar... They\u2019re not consistent. So you\u2019d want that consistency of intelligence across the board.\" \u2014 **Demis Hassabis** (DeepMind Co-founder) \n> Watch: [Episode 475: Demis Hassabis: Future of AI, Simulating Reality, Physics and Video Games](https://www.youtube.com/watch?v=-HzgcbRXUK8&t=3153s)\n\nYann LeCun cautions that true AGI is still \"not just around the corner,\" likely requiring a decade or more because of many unresolved challenges:\n> \"Are we going to have systems that can reason and plan... all of this is going to take at least a decade and probably much more... I\u2019ve been hearing people for the last 12, 15 years claiming that AGI is just around the corner and being systematically wrong.\" \u2014 **Yann LeCun** (AI Research Pioneer) \n> Watch: [Episode 416: Yann Lecun: Meta AI, Open Source, Limits of LLMs, AGI & the Future of AI](https://www.youtube.com/watch?v=5t1vTLU7s40&t=7537s)\n\nOther experts note societal risks and transformative power: Dylan Patel worries about techno-fascism and concentration of power, while Nathan Lambert stresses human goodness and physical constraints as factors preventing catastrophic AI takeover.\n\n- [Episode 431: Roman Yampolskiy: Dangers of Superintelligent AI](https://www.youtube.com/watch?v=NNr6gPelJ3E)\n- [Episode 471: Sundar Pichai: CEO of Google and Alphabet](https://www.youtube.com/watch?v=9V6tWC4CdFQ)\n- [Episode 475: Demis Hassabis: Future of AI, Simulating Reality, Physics and Video Games](https://www.youtube.com/watch?v=-HzgcbRXUK8)\n- [Episode 416: Yann Lecun: Meta AI, Open Source, Limits of LLMs, AGI & the Future of AI](https://www.youtube.com/watch?v=5t1vTLU7s40)\n- [Episode 459: DeepSeek, China, OpenAI, NVIDIA, xAI, TSMC, Stargate, and AI Megaclusters](https://www.youtube.com/watch?v=_1f-o0nqpEI)", "type": "text" } ] } ], "feedback": { "helpful": true, "text": "Thanks. I will start with episode 471. It was a very quick and cool recommendation." } }, { "timestamp": "2026-02-07T09:39:21.660537", "turns": [ { "role": "user", "content": [ { "text": "What is the best advice from Pavel Durov in terms of habits and self-discipline?", "type": "text" } ] }, { "role": "assistant", "content": [ { "text": "Pavel Durov's best advice for habits and self-discipline is to consistently train the \"muscle\" of self-discipline through daily routines like intense physical exercise (e.g., hundreds of push-ups and squats) and confronting mental challenges directly by starting tasks even when motivation is low. He emphasizes that action comes before feeling motivated, and developing discipline enables overcoming negativity and achieving long-term goals.\n\nHere are some of his exact words:\n\n> \"I do 300 push-ups and 300 squats every morning... they\u2019re definitely a good way to practice self-discipline because you don\u2019t want to do these push-ups in the morning most of the days... The main muscle you can exercise is this muscle, the muscle of self-discipline... Because if you get to train that one, everything else just comes by itself.\" \u2014 **Pavel Durov** (Telegram Founder & CEO) \n> Watch: [Episode 482: Pavel Durov: Telegram, Freedom, Censorship, Money, Power & Human Nature](https://www.youtube.com/watch?v=qjPH9njnaVU&t=1412s)\n\n> \"Self-discipline is particularly important because without it, how can you overcome this seemingly endless loop of negativity or despair... I start doing things... You gain energy by doing something, so you start doing something, then it happens, you feel motivated, you feel inspired.\" \u2014 **Pavel Durov** (Telegram Founder & CEO) \n> Watch: [Episode 482: Pavel Durov: Telegram, Freedom, Censorship, Money, Power & Human Nature](https://www.youtube.com/watch?v=qjPH9njnaVU&t=1231s)\n\n> \"There are many days when you don\u2019t want to start working out, but you have to overcome this initial reluctance, and then you get to a point that you enjoy it... You need to write a novel or just write the paragraph... You need to write some code first, and then you get inspired.\" \u2014 **Pavel Durov** (Telegram Founder & CEO) \n> Watch: [Episode 482: Pavel Durov: Telegram, Freedom, Censorship, Money, Power & Human Nature](https://www.youtube.com/watch?v=qjPH9njnaVU&t=1332s)", "type": "text" } ] } ], "feedback": { "helpful": true, "text": "Brilliant, it was incredibly helpful. Thank you." } }, { "timestamp": "2026-02-07T09:43:09.616321", "turns": [ { "role": "user", "content": [ { "text": "What habits and routines do high performers follow?", "type": "text" } ] }, { "role": "assistant", "content": [ { "text": "High performers emphasize consistency in daily habits, prioritizing focus and rest, combining physical exercise with mental routines like deep work and mindfulness. They also protect peak focus hours fiercely, maintain social interaction rituals, and use strategic breaks like non-sleep deep rest to recharge.\n\n> \"I have a rule for myself that I do a set of tasks for at least five minutes every day... One of them is playing guitar... I wake up. If I don\u2019t feel I slept enough, I do this non-sleep deep rest yoga nidra... I punch some caffeine down... resistance train three days a week, run three days a week and then take one day off, and like to be done by 8:39 and then I want to get into some real work.\" \u2014 **Andrew Huberman** (Neuroscientist) \n> Watch: [Episode 435: Andrew Huberman: Focus, Controversy, Politics, and Relationships](https://www.youtube.com/watch?v=ZIyB9e_7a4c&t=5766s)\n\n> \"It\u2019s all about focus in the moment... How much total focus can you give to something? And then I like to take walks and think about things... learning to turn it off and engage with people socially... The whiteboard is such a valuable tool... Then just churn through and just churn through.\" \u2014 **Andrew Huberman** (Neuroscientist) \n> Watch: [Episode 393: Andrew Huberman: Relationships, Drama, Betrayal, Sex, and Love](https://www.youtube.com/watch?v=eTBAxD6lt2g&t=6713s)\n\n> \"My routine on a good day, I do about half an hour of cardio and I do about forty-five minutes of weightlifting... Puttering, coffee, gym, and then work... It\u2019s better just to carve out the time for people.\" \u2014 **Jeff Bezos** (Founder of Amazon & Blue Origin) \n> Watch: [Episode 405: Jeff Bezos: Amazon and Blue Origin](https://www.youtube.com/watch?v=DcWqzZ3I2cY&t=7012s)\n\nYou might find these episodes insightful for in-depth habits of high performers:\n\n- [Episode 435: Andrew Huberman: Focus, Controversy, Politics, and Relationships](https://www.youtube.com/watch?v=ZIyB9e_7a4c)\n- [Episode 393: Andrew Huberman: Relationships, Drama, Betrayal, Sex, and Love](https://www.youtube.com/watch?v=eTBAxD6lt2g)\n- [Episode 405: Jeff Bezos: Amazon and Blue Origin](https://www.youtube.com/watch?v=DcWqzZ3I2cY)", "type": "text" } ] } ], "feedback": { "helpful": true, "text": "Thank you for your recommendation. I'm on it! " } }, { "timestamp": "2026-02-07T10:21:38.721516", "turns": [ { "role": "user", "content": [ { "text": "How much time do I need to spend on work a day?", "type": "text" } ] }, { "role": "assistant", "content": [ { "text": "Highly productive people and founders often suggest that about 4 hours of deeply focused work a day can be enough to achieve great progress, rather than long exhaustive hours. It's more about quality and avoiding distractions than pure quantity.\n\n> \"40 hours a week is actually a ton if you don\u2019t piss it away. Most people do piss it away... even three hours, four hours of concentrated uninterrupted time every day would move the goals they truly care about way down the field.\" \u2014 **DHH** (Legendary Programmer) \n> Watch: [Episode 474: DHH: Future of Programming, AI, Ruby on Rails, Productivity & Parenting](https://www.youtube.com/watch?v=vagyIcmIGOQ&t=16065s)\n\n> \"If you\u2019ve really put in the deep work, two or three bouts per day by about five or 6:00 PM, it\u2019s over.\" \u2014 **Andrew Huberman** (Neuroscientist) \n> Watch: [Episode 435: Andrew Huberman: Focus, Controversy, Politics, and Relationships](https://www.youtube.com/watch?v=ZIyB9e_7a4c&t=6151s)\n\n> \"I used to need really long stretches where I would do all-nighters and stuff to get shit done. But I\u2019ve gotten trained to have more interruptions where I can... So, I think that works for me.\" \u2014 **Pieter Levels** (Digital Nomad Entrepreneur) \n> Watch: [Episode 440: Pieter Levels: Programming, Viral AI Startups, and Digital Nomad Life](https://www.youtube.com/watch?v=oFtjKbXKqbg&t=10895s)\n\nThis suggests that highly productive individuals focus on structuring their time to achieve deep, focused work segments of a few hours rather than grinding an entire day without breaks. Quality focus is the multiplier, not just hours logged.", "type": "text" } ] } ], "feedback": { "helpful": true, "text": "Amazing, very insightful. I would like to find out more about Pieter Levels' podcast and best practices. " } }, { "timestamp": "2026-02-13T06:34:19.485253", "turns": [ { "role": "user", "content": [ { "text": "What's Pavel Durov's nutrition and health routine? ", "type": "text" } ] }, { "role": "assistant", "content": [ { "text": "Pavel Durov maintains a disciplined physical and nutritional routine focused on body-weight exercises, gym workouts, intermittent fasting, and a diet centered mostly on seafood and vegetables while avoiding red meat and processed sugar. He views training self-discipline as the core benefit over physical changes.\n\n> \"I do 300 push-ups and 300 squats every morning. And in addition to that, I go to the gym normally five, six times a week, spending between one and two hours every day... when I can, I also take an ice bath because it\u2019s another exercise of self-discipline. I think the main muscle you can exercise is this muscle, the muscle of self-discipline.\" \u2014 **Pavel Durov** (Telegram Founder & CEO) \n> Watch: [Episode 482: Pavel Durov: Telegram, Freedom, Censorship, Money, Power & Human Nature](https://www.youtube.com/watch?v=qjPH9njnaVU&t=1412s)\n\n> \"No, I\u2019m not militant about sugar... Red meat, I stopped eating it about 20 years ago because I just felt heavy every time I had it... So I normally eat seafood of all kinds and vegetables. This is the basic source of calories for me.\" \u2014 **Pavel Durov** \n> Watch: [Episode 482: Pavel Durov: Telegram, Freedom, Censorship, Money, Power & Human Nature](https://www.youtube.com/watch?v=qjPH9njnaVU&t=1968s)\n\n> \"Intermittent fasting. So eating only within six hours and not eating for 18 hours every day also brings structure into your day and into your eating habits... sugar is harmful.\" \u2014 **Pavel Durov** \n> Watch: [Episode 482: Pavel Durov: Telegram, Freedom, Censorship, Money, Power & Human Nature](https://www.youtube.com/watch?v=qjPH9njnaVU&t=1881s)\n\nHe also emphasizes physical activity as key to productivity and mental clarity, not just health.\n\n> \"Physical activity is the only way I know of... It\u2019s also being productive. It\u2019s also being stress resilient... I can instantly feel that stress is creeping on me when I can\u2019t train.\" \u2014 **Pavel Durov** \n> Watch: [Episode 482: Pavel Durov: Telegram, Freedom, Censorship, Money, Power & Human Nature](https://www.youtube.com/watch?v=qjPH9njnaVU&t=1773s)", "type": "text" } ] } ], "feedback": { "helpful": true, "text": "Thanks, it was very quick to find the episode I needed. " } } ]