Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

This morning at NeurIPS, Rich Sutton reminded us that we need continual learning to reach AGI. This afternoon, Ali Behrouz presented a Google poster paper, Nested Learning, which provides new ideas on the path to continual learning. I recorded the 40 minute talk as it might be useful for...

PTrubey's profile picture

Phil Trubey

14,116 subscribers

235,587 Aufrufe • vor 8 Monaten •via X (Twitter)

BildungWissenschaft & Technologie
LIVE

Anya Rossi• Live Now

Private livecam show

0 Kommentare

Keine Kommentare verfügbar

Kommentare vom Original-Post werden hier angezeigt

Ähnliche Videos

Continual Learning in 2026. And AGI with it? In July, Dario said he believes Continual Learning will turn out to be not as difficult as it seems. Sholto Douglas, Anthropic and former Deepmind researcher, predicted Continual Learning gets solved in a satisfying way in 2026. Sholto said that last week. Considering how capable AI models have become in 2025, it is unwise to dismiss this as fundraising or hype. It is much wiser to assume AGI is coming. That it will change the world. And that you can benefit from it... ...than it is to assume the opposite. "Not enough people are ready for AI to not be a bubble." - roon Choose wisely my friends.
0:26

Continual Learning in 2026. And AGI with it? In July, Dario said he believes Continual Learning will turn out to be not as difficult as it seems. Sholto Douglas, Anthropic and former Deepmind researcher, predicted Continual Learning gets solved in a satisfying way in 2026. Sholto said that last week. Considering how capable AI models have become in 2025, it is unwise to dismiss this as fundraising or hype. It is much wiser to assume AGI is coming. That it will change the world. And that you can benefit from it... ...than it is to assume the opposite. "Not enough people are ready for AI to not be a bubble." - roon Choose wisely my friends.

Dan McAteer

69,496 Aufrufe • vor 8 Monaten

.Richard Sutton, father of reinforcement learning, doesn’t think LLMs are bitter-lesson-pilled. My steel man of Richard’s position: we need some new architecture to enable continual (on-the-job) learning. And if we have continual learning, we don't need a special training phase - the agent just learns on-the-fly - like all humans, and indeed, like all animals. This new paradigm will render our current approach with LLMs obsolete. I did my best to represent the view that LLMs will function as the foundation on which this experiential learning can happen. Some sparks flew. 0:00:00 – Are LLMs a dead-end? 0:13:51 – Do humans do imitation learning? 0:23:57 – The Era of Experience 0:34:25 – Current architectures generalize poorly out of distribution 0:42:17 – Surprises in the AI field 0:47:28 – Will The Bitter Lesson still apply after AGI? 0:54:35 – Succession to AI
1:07:08

.Richard Sutton, father of reinforcement learning, doesn’t think LLMs are bitter-lesson-pilled. My steel man of Richard’s position: we need some new architecture to enable continual (on-the-job) learning. And if we have continual learning, we don't need a special training phase - the agent just learns on-the-fly - like all humans, and indeed, like all animals. This new paradigm will render our current approach with LLMs obsolete. I did my best to represent the view that LLMs will function as the foundation on which this experiential learning can happen. Some sparks flew. 0:00:00 – Are LLMs a dead-end? 0:13:51 – Do humans do imitation learning? 0:23:57 – The Era of Experience 0:34:25 – Current architectures generalize poorly out of distribution 0:42:17 – Surprises in the AI field 0:47:28 – Will The Bitter Lesson still apply after AGI? 0:54:35 – Succession to AI

Dwarkesh Patel

3,086,965 Aufrufe • vor 11 Monaten

How to extract data from papers for literature review in seconds? 1. Go to 2. Upload 2-3 papers you already know are relevant 3. Start with clicking on one paper 4. ResearchCollab do the following for the paper ✦ Provide a short overview of the paper ✦ Identify weaknesses in the paper ✦ Share papers that contrast the existing paper ✦ Extract meta data about the paper ✦ Evaluate each part (e.g., methodology) of the paper ✦ Provide AI chat to extract any other data 5. Now click on the Related Papers button at top right 6. You will get papers related to the seed paper 7. You can click on each paper and read its abstract 8. If you find it relevant, just add it to your list of papers 9. Do the same for the other 2 seed papers 10. This way you will collect all relevant papers 11. And extract data from those papers After this, analyse the data and report the findings. Try ResearchCollab today:
0:47

How to extract data from papers for literature review in seconds? 1. Go to 2. Upload 2-3 papers you already know are relevant 3. Start with clicking on one paper 4. ResearchCollab do the following for the paper ✦ Provide a short overview of the paper ✦ Identify weaknesses in the paper ✦ Share papers that contrast the existing paper ✦ Extract meta data about the paper ✦ Evaluate each part (e.g., methodology) of the paper ✦ Provide AI chat to extract any other data 5. Now click on the Related Papers button at top right 6. You will get papers related to the seed paper 7. You can click on each paper and read its abstract 8. If you find it relevant, just add it to your list of papers 9. Do the same for the other 2 seed papers 10. This way you will collect all relevant papers 11. And extract data from those papers After this, analyse the data and report the findings. Try ResearchCollab today:

Faheem Ullah

26,494 Aufrufe • vor 6 Monaten

Continual learning sometimes gets discussed as if the goal is to dissolve the context/weights distinction. Let the model just keep accumulating, fine-tuning itself on the fly. Andrej Karpathy points out, though, that this isn't how humans do it. Our working memory gets wiped regularly. What we actually have is a consolidation process (sleep) that distills stuff into the brain, in a weird and lossy way. This is very different from how people sometimes talk about continual learning. It's not obvious it's something you can get for free from doing long enough RL loops.
3:21

Continual learning sometimes gets discussed as if the goal is to dissolve the context/weights distinction. Let the model just keep accumulating, fine-tuning itself on the fly. Andrej Karpathy points out, though, that this isn't how humans do it. Our working memory gets wiped regularly. What we actually have is a consolidation process (sleep) that distills stuff into the brain, in a weird and lossy way. This is very different from how people sometimes talk about continual learning. It's not obvious it's something you can get for free from doing long enough RL loops.

Dwarkesh Patel

59,993 Aufrufe • vor 3 Monaten

Why getting reach here is so difficult. Everyone is in a war to get on the For You feed. This is X Pro. We will talk about how the algorithm picks from all this. Tonight on ’s space at 7 p.m. pacific. And I only have a very small part of X’s users in lists. It took me 18 years to build this. You can have it in just a minute. Link below.
8:30

Why getting reach here is so difficult. Everyone is in a war to get on the For You feed. This is X Pro. We will talk about how the algorithm picks from all this. Tonight on ’s space at 7 p.m. pacific. And I only have a very small part of X’s users in lists. It took me 18 years to build this. You can have it in just a minute. Link below.

Robert Scoble

20,214 Aufrufe • vor 1 Jahr

NS Rb: Thank you for remembering that it's been six years. Right now, this feels like the best day of my life. Starting all the way back from the VALORANT beta in 2020, I think I always viewed myself more as someone who was still learning. Honestly, I never really thought of myself as someone who could just guarantee that I was a great player. So from the members I played with starting in Vision Strikers through DRX up until 2023, I think I spent those three years learning. Then through that learning, when I went to TEC in VCT CN, I thought a lot about how to use what I had learned, not just in-game but also more broadly in life. And that eventually brought me here to Nongshim and to this moment. In the end, though, the result came down to learning, studying, teammates covering for one another, and most importantly, as obvious as it sounds, hard work. (via EndPoem)
4:26

NS Rb: Thank you for remembering that it's been six years. Right now, this feels like the best day of my life. Starting all the way back from the VALORANT beta in 2020, I think I always viewed myself more as someone who was still learning. Honestly, I never really thought of myself as someone who could just guarantee that I was a great player. So from the members I played with starting in Vision Strikers through DRX up until 2023, I think I spent those three years learning. Then through that learning, when I went to TEC in VCT CN, I thought a lot about how to use what I had learned, not just in-game but also more broadly in life. And that eventually brought me here to Nongshim and to this moment. In the end, though, the result came down to learning, studying, teammates covering for one another, and most importantly, as obvious as it sounds, hard work. (via EndPoem)

VALO2ASIA

58,285 Aufrufe • vor 5 Monaten

"We Need to Employ $50 Trillion": Larry Fink on Why the Private Sector Must Lead the Green Transition "Well, if they don't get it done, then we are going to have more risk as societies, we're going to have more issues related to rising climate and importantly, which will create more societal issues." "Already we're seeing an impact in society right now from climate risk and climate change. are seeing insurance premiums going up 18 % a year right now. So we're seeing a real impact from what climate risk is doing from flooding, from fires. So we're seeing a big impact." "And so the faster that we could find ways to mitigating the rising temperatures, I would say the more just society could be. And so to me, we don't have much time. And this is why when I learned about catalyst and I learned about what Bill was doing was very clear to me why we needed to be a part of this, why we needed to invest the time and the money." "And the key is also the time because we need to be learning about these new the new technologies and how to move forward. And we need to then inform our investors ultimately where we think the next opportunities are going to be too as Bill in his book wrote about, we need to employ $50 trillion to get to a green world." "With the rising deficits that we see in governments, from our perspective, the 50 trillion is mostly going to have to come from the private sector. And I do believe that money will be well spent, well spent for returns. It will transform our economies. It will build new jobs. will build new cities and new opportunities." "So I look at this as an optimist. I don't look at this as a pessimist. But the key is to be that optimist. We have to jump on it now. We have to be investing today. We need to talk about it today, although much of the problems in the future but we're seeing more and more evidence of the problem today."
2:24

"We Need to Employ $50 Trillion": Larry Fink on Why the Private Sector Must Lead the Green Transition "Well, if they don't get it done, then we are going to have more risk as societies, we're going to have more issues related to rising climate and importantly, which will create more societal issues." "Already we're seeing an impact in society right now from climate risk and climate change. are seeing insurance premiums going up 18 % a year right now. So we're seeing a real impact from what climate risk is doing from flooding, from fires. So we're seeing a big impact." "And so the faster that we could find ways to mitigating the rising temperatures, I would say the more just society could be. And so to me, we don't have much time. And this is why when I learned about catalyst and I learned about what Bill was doing was very clear to me why we needed to be a part of this, why we needed to invest the time and the money." "And the key is also the time because we need to be learning about these new the new technologies and how to move forward. And we need to then inform our investors ultimately where we think the next opportunities are going to be too as Bill in his book wrote about, we need to employ $50 trillion to get to a green world." "With the rising deficits that we see in governments, from our perspective, the 50 trillion is mostly going to have to come from the private sector. And I do believe that money will be well spent, well spent for returns. It will transform our economies. It will build new jobs. will build new cities and new opportunities." "So I look at this as an optimist. I don't look at this as a pessimist. But the key is to be that optimist. We have to jump on it now. We have to be investing today. We need to talk about it today, although much of the problems in the future but we're seeing more and more evidence of the problem today."

Camus

55,484 Aufrufe • vor 1 Jahr

this was the most important bit of the ilya interview imo. humans are not AGI, and LLMs won’t become like humans with more scaling. humans lack a huge amount of knowledge and have insanely good “continual learning” powered by extremely good reward functions (except for addiction) that guide them. and so it’s more about the learning rather than knowledge. the term AGI was coined as a response to the narrow AI which was only capable of intelligence in a specific domain (chess, game, code, etc) but General intelligence is able to learn different topics because that’s what “learning” is about. pre-training was thought to be the solution to reaching AGI because you train AI on so many different topics. but they have “overshot” that target. amazing perspective.
1:57

this was the most important bit of the ilya interview imo. humans are not AGI, and LLMs won’t become like humans with more scaling. humans lack a huge amount of knowledge and have insanely good “continual learning” powered by extremely good reward functions (except for addiction) that guide them. and so it’s more about the learning rather than knowledge. the term AGI was coined as a response to the narrow AI which was only capable of intelligence in a specific domain (chess, game, code, etc) but General intelligence is able to learn different topics because that’s what “learning” is about. pre-training was thought to be the solution to reaching AGI because you train AI on so many different topics. but they have “overshot” that target. amazing perspective.

ℏεsam

53,444 Aufrufe • vor 9 Monaten

I built a Visual Studio Code extension to turn Visual Studio code into a custom learning environment for my Machine Learning class. Attached, you'll see a 2-minute video of how it works. I haven't tried this with my students yet (the February cohort will be the first to do so), but I think it will be huge. I wish more people would offer a learning experience like this. My next cohort starts in February and you can join at You'll get lifetime access to the best Machine Learning engineering cohort online.
2:43

I built a Visual Studio Code extension to turn Visual Studio code into a custom learning environment for my Machine Learning class. Attached, you'll see a 2-minute video of how it works. I haven't tried this with my students yet (the February cohort will be the first to do so), but I think it will be huge. I wish more people would offer a learning experience like this. My next cohort starts in February and you can join at You'll get lifetime access to the best Machine Learning engineering cohort online.

Santiago

82,846 Aufrufe • vor 1 Jahr

A Talk About AI That Will Blow Your Mind. It Did In 1998 When I Attended The Talk. I just found this video from 1998 when I attended this talk by Rupert Sheldrake, Terence McKenna and Ralph Abraham at the University of California, Santa Cruz to explore how machine intelligence might evolve in relation to our own. I never thought I would see this again and it had a great influence on me in the AI I was building in that era and on to today. But ai just found a copy. I certainly did not run around with a VHS recorder so I am blown away that this exists. Now you can see what I saw. At that time, the internet was still young, and artificial intelligence belonged mostly to science fiction. Yet many of the questions we raised then have become part of daily life. In this conversation, it was explored whether intelligence is best understood as logic and computation, or as something embodied, participatory, and alive. Can the mind be reduced to code, or does life itself depend on forms of knowing that no algorithm can contain? AI now outpace us in speed, reach, and memory. Yet the deeper mystery is not how far they can go, but what they reveal about mind and ourselves. Will AI reproduce the limitations of our mechanistic worldview, or might it help us rediscover dimensions of mind that transcend machinery altogether? It's striking how near we now are to the possibilities we once only speculated about. Quantum computing, self-learning systems, large language models very much as Terence describes—and the looming prospect of superintelligence—have moved from the margins to the mainstream. But the heart of the conversation remains just as relevant today, if not more so: what is consciousness, and how might we participate in its unfolding evolution?
42:37

A Talk About AI That Will Blow Your Mind. It Did In 1998 When I Attended The Talk. I just found this video from 1998 when I attended this talk by Rupert Sheldrake, Terence McKenna and Ralph Abraham at the University of California, Santa Cruz to explore how machine intelligence might evolve in relation to our own. I never thought I would see this again and it had a great influence on me in the AI I was building in that era and on to today. But ai just found a copy. I certainly did not run around with a VHS recorder so I am blown away that this exists. Now you can see what I saw. At that time, the internet was still young, and artificial intelligence belonged mostly to science fiction. Yet many of the questions we raised then have become part of daily life. In this conversation, it was explored whether intelligence is best understood as logic and computation, or as something embodied, participatory, and alive. Can the mind be reduced to code, or does life itself depend on forms of knowing that no algorithm can contain? AI now outpace us in speed, reach, and memory. Yet the deeper mystery is not how far they can go, but what they reveal about mind and ourselves. Will AI reproduce the limitations of our mechanistic worldview, or might it help us rediscover dimensions of mind that transcend machinery altogether? It's striking how near we now are to the possibilities we once only speculated about. Quantum computing, self-learning systems, large language models very much as Terence describes—and the looming prospect of superintelligence—have moved from the margins to the mainstream. But the heart of the conversation remains just as relevant today, if not more so: what is consciousness, and how might we participate in its unfolding evolution?

Brian Roemmele

147,955 Aufrufe • vor 9 Monaten

PhD Students – How to extract data from papers for your literature review in seconds? Extracting data from papers takes a lot of time. You can automate this process with Bohrium 𝐇𝐨𝐰 𝐭𝐨 𝐚𝐮𝐭𝐨𝐦𝐚𝐭𝐢𝐜𝐚𝐥𝐥𝐲 𝐞𝐱𝐭𝐫𝐚𝐜𝐭 𝐝𝐚𝐭𝐚 𝐟𝐫𝐨𝐦 𝐩𝐚𝐩𝐞𝐫𝐬? 1. Go to and log in 2. Click on 𝐾𝑛𝑜𝑤𝑙𝑒𝑑𝑔𝑒 𝐵𝑎𝑠𝑒 from the left menu 3. Upload the papers you selected for literature review 4. You will see the following option against each paper - Read PDF - Key Takeaway - AI Poster 5. Click on 𝑅𝑒𝑎𝑑 𝑃𝐷𝐹 for the first paper in your list 6. Write a prompt for the data you want to extract 7. For example, you can enter datasets, methodology etc. 8. It will extract the required data from the paper 9. If you want to extract Key Takeaways from the paper 10. Go back and click on 𝐾𝑒𝑦 𝑇𝑎𝑘𝑒𝑎𝑤𝑎𝑦𝑠 11. Bohrium will extract Key Takeaways from the paper 12. In addition to this, you also have 2 more options - AI Poster - Podcast 13. Click on 𝐴𝐼 𝑃𝑜𝑠𝑡𝑒𝑟 and it will create a poster for you 14. This is the poster based on the given research paper 15. If you click on 𝑃𝑜𝑑𝑐𝑎𝑠𝑡, it will convert the paper to audio 16. You can listen to the paper instead of reading it Repeat this cycle for all the papers in your pool. You will end up with the required data. You can use this data to write your literature review Try Bohrium today for FREE: Anything you’d like to add?
0:59

PhD Students – How to extract data from papers for your literature review in seconds? Extracting data from papers takes a lot of time. You can automate this process with Bohrium 𝐇𝐨𝐰 𝐭𝐨 𝐚𝐮𝐭𝐨𝐦𝐚𝐭𝐢𝐜𝐚𝐥𝐥𝐲 𝐞𝐱𝐭𝐫𝐚𝐜𝐭 𝐝𝐚𝐭𝐚 𝐟𝐫𝐨𝐦 𝐩𝐚𝐩𝐞𝐫𝐬? 1. Go to and log in 2. Click on 𝐾𝑛𝑜𝑤𝑙𝑒𝑑𝑔𝑒 𝐵𝑎𝑠𝑒 from the left menu 3. Upload the papers you selected for literature review 4. You will see the following option against each paper - Read PDF - Key Takeaway - AI Poster 5. Click on 𝑅𝑒𝑎𝑑 𝑃𝐷𝐹 for the first paper in your list 6. Write a prompt for the data you want to extract 7. For example, you can enter datasets, methodology etc. 8. It will extract the required data from the paper 9. If you want to extract Key Takeaways from the paper 10. Go back and click on 𝐾𝑒𝑦 𝑇𝑎𝑘𝑒𝑎𝑤𝑎𝑦𝑠 11. Bohrium will extract Key Takeaways from the paper 12. In addition to this, you also have 2 more options - AI Poster - Podcast 13. Click on 𝐴𝐼 𝑃𝑜𝑠𝑡𝑒𝑟 and it will create a poster for you 14. This is the poster based on the given research paper 15. If you click on 𝑃𝑜𝑑𝑐𝑎𝑠𝑡, it will convert the paper to audio 16. You can listen to the paper instead of reading it Repeat this cycle for all the papers in your pool. You will end up with the required data. You can use this data to write your literature review Try Bohrium today for FREE: Anything you’d like to add?

Faheem Ullah

13,433 Aufrufe • vor 1 Jahr

I never do this ever but I feel that as a streamer for the game I love as well as the peeps who play it with me that this needs to be addressed. We are going to talk about the toxic behaviour and mentality of people in Unite. This individual is well known in my region to be extremely unfair spamming thanks... going afk... and surrendering constantly in their matches when things aren't going their way. For the first time for me, they've opened up voice comms and proceeded to trash talk myself and my friend. At first it was laughable because our region knows what type of person this player is. When the match ended, they continually talked negatively in such way that was in poor taste and it was then and there that I had to bring this to light. When we checked the aftermath... he made little to no contribution as a team player but proceeded to blame us. You just simply cannot be talking negatively like this without taking "accountability" for your own actions. I get that some games are frustrating and you can get upset but I strive with 100% everytime I play this game to make the community I play with a positive/learning and enjoyable experience. I understand there are those who were worried about how people may take this and are looking out for me and I appreciate you guys heaps. I am writing this to share that IT IS NOT OKAY to talk and act like this.. at least not to me or those around me let alone anyone else. Be a better person 🥹
2:26

I never do this ever but I feel that as a streamer for the game I love as well as the peeps who play it with me that this needs to be addressed. We are going to talk about the toxic behaviour and mentality of people in Unite. This individual is well known in my region to be extremely unfair spamming thanks... going afk... and surrendering constantly in their matches when things aren't going their way. For the first time for me, they've opened up voice comms and proceeded to trash talk myself and my friend. At first it was laughable because our region knows what type of person this player is. When the match ended, they continually talked negatively in such way that was in poor taste and it was then and there that I had to bring this to light. When we checked the aftermath... he made little to no contribution as a team player but proceeded to blame us. You just simply cannot be talking negatively like this without taking "accountability" for your own actions. I get that some games are frustrating and you can get upset but I strive with 100% everytime I play this game to make the community I play with a positive/learning and enjoyable experience. I understand there are those who were worried about how people may take this and are looking out for me and I appreciate you guys heaps. I am writing this to share that IT IS NOT OKAY to talk and act like this.. at least not to me or those around me let alone anyone else. Be a better person 🥹

Nuggie

27,103 Aufrufe • vor 3 Jahren

Every time I found myself in an unfamiliar situation in my cricketing career, I never let it get me down. Instead, I adapted to it by learning. Early in my career, the T20 format was introduced. I trained hard for it and learnt to play it. Learning made me confident in something I had never done. It is this very habit of learning that made me confident enough to play all the formats in different conditions around the world. The learning didn’t stop even after I retired. I learnt to be a coach and a mentor. That’s why I like what I have done with the people at CoinDCX : India Ka Crypto Coach. We share a common belief “Learning is the only way to succeed.” #ConfidentCryptoStart #Ad
0:45

Every time I found myself in an unfamiliar situation in my cricketing career, I never let it get me down. Instead, I adapted to it by learning. Early in my career, the T20 format was introduced. I trained hard for it and learnt to play it. Learning made me confident in something I had never done. It is this very habit of learning that made me confident enough to play all the formats in different conditions around the world. The learning didn’t stop even after I retired. I learnt to be a coach and a mentor. That’s why I like what I have done with the people at CoinDCX : India Ka Crypto Coach. We share a common belief “Learning is the only way to succeed.” #ConfidentCryptoStart #Ad

Gautam Gambhir

330,891 Aufrufe • vor 1 Jahr

Experiments in progress. The one on the right has been learning for ~3 hours, the one in the middle for ~1 hour, and the one on the left just started a few minutes ago. The initial motivation for making the physical Atari was just to commit ourselves to a subset of algorithms that can make progress in this setup. This commitment rules out algorithms that require billions of samples to learn (or worse, require multiple environments running in parallel). Atari games are simple enough that we should be able to show learning on them in a short amount of time with no prior knowledge. Since then, I've realized that this setup is also a good way to compare different paradigms in robotics in a principled way. These paradigms are sim2real, learning from tele-operated data, and learning directly on the robots. So far, I have observed that getting sim2real to work reliably is hard. It requires tweaks that don't scale. Policies that can play perfectly in simulation fall apart because of latencies and the messiness of the real world. These aspects could be modeled to improve the simulation, but not without sinking significant human engineering hours. I have higher hopes for learning from tele-operated data, but that requires a human to learn the task first. These experiments are on my to-do list. I have to learn to play some of the games well through the robot. I’m half-decent at playing Pong and Ms Pacman now. Learning directly on robots is looking like the most promising approach. This approach takes away pesky distribution shifts and makes it possible to have algorithms that continually improve with more data and time without any human intervention. It feels great to let experiments run overnight and wake up to find improved policies. With learning on robots, I should, in principle, be able to go on a long vacation and come back to find better policies for complex tasks beyond Atari games. Whether that is possible with current learning algorithms is a different question.
1:05

Experiments in progress. The one on the right has been learning for ~3 hours, the one in the middle for ~1 hour, and the one on the left just started a few minutes ago. The initial motivation for making the physical Atari was just to commit ourselves to a subset of algorithms that can make progress in this setup. This commitment rules out algorithms that require billions of samples to learn (or worse, require multiple environments running in parallel). Atari games are simple enough that we should be able to show learning on them in a short amount of time with no prior knowledge. Since then, I've realized that this setup is also a good way to compare different paradigms in robotics in a principled way. These paradigms are sim2real, learning from tele-operated data, and learning directly on the robots. So far, I have observed that getting sim2real to work reliably is hard. It requires tweaks that don't scale. Policies that can play perfectly in simulation fall apart because of latencies and the messiness of the real world. These aspects could be modeled to improve the simulation, but not without sinking significant human engineering hours. I have higher hopes for learning from tele-operated data, but that requires a human to learn the task first. These experiments are on my to-do list. I have to learn to play some of the games well through the robot. I’m half-decent at playing Pong and Ms Pacman now. Learning directly on robots is looking like the most promising approach. This approach takes away pesky distribution shifts and makes it possible to have algorithms that continually improve with more data and time without any human intervention. It feels great to let experiments run overnight and wake up to find improved policies. With learning on robots, I should, in principle, be able to go on a long vacation and come back to find better policies for complex tasks beyond Atari games. Whether that is possible with current learning algorithms is a different question.

Khurram Javed

52,110 Aufrufe • vor 8 Monaten

Asmongold feels bad for being in favor of Blizzard during the harassment scandal, saying it wasn't as true as it seemed 👀 "I feel kind of bad about this. I do, because at the time, I was very much in favour of the Blizzard harassment scandal, and to be fair, there was not really a lot of evidence to say the contrary But I do kind of feel bad that I was a part of this, and I enabled this to the degree that I did. And it seems like it wasn't really as true as it seemed out to be. We all were. I think that everybody kind of believed it”
0:53

Asmongold feels bad for being in favor of Blizzard during the harassment scandal, saying it wasn't as true as it seemed 👀 "I feel kind of bad about this. I do, because at the time, I was very much in favour of the Blizzard harassment scandal, and to be fair, there was not really a lot of evidence to say the contrary But I do kind of feel bad that I was a part of this, and I enabled this to the degree that I did. And it seems like it wasn't really as true as it seemed out to be. We all were. I think that everybody kind of believed it”

Prism

60,724 Aufrufe • vor 24 Tagen

I love this interview with Sam Whitmore because it weaves in agentic memory, continual learning, user goal alignment, predictions for what's next... with the playfulness and whimsy of growing a young family while staying on the frontier of tech 🤍 a reminder that Cursor is hiring, & to reach out to Sam Whitmore to learn more
1:07

I love this interview with Sam Whitmore because it weaves in agentic memory, continual learning, user goal alignment, predictions for what's next... with the playfulness and whimsy of growing a young family while staying on the frontier of tech 🤍 a reminder that Cursor is hiring, & to reach out to Sam Whitmore to learn more

ashe

13,222 Aufrufe • vor 4 Monaten

Let's take a walk through town! A lot of people weren't happy about the sprite scaling so I have redrawn the party and npcs to be at the right scale to the town. It is still a learning experience drawing at this size so hopefully I can improve as things go along.
0:33

Let's take a walk through town! A lot of people weren't happy about the sprite scaling so I have redrawn the party and npcs to be at the right scale to the town. It is still a learning experience drawing at this size so hopefully I can improve as things go along.

David - Nostalgic Realms - Lair of the Leviathan

15,246 Aufrufe • vor 1 Jahr