Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

.Trenton Bricken explains how we know LLMs are actually generalizing - aka they're not just stochastic parrots: - Training models on code makes them better at reasoning in language. - Models fine tuned on math problems become better at entity detection. - We can just straightforwardly read the world-models... show more

Dwarkesh Patel

242,712 subscribers

237,812 views • 2 years ago •via X (Twitter)

Science & Technology Education

Anya Rossi• Live Now

Private livecam show

10 Comments

akash2 years ago

@TrentonBricken Papers that Trenton is talking about in this clip — 1. 2.

Dave 8x7B2 years ago

@TrentonBricken looks like another banger @dwarkesh_sp! your meteoric rise to popularity online has been fun to watch! Keep on, man!

Dwarkesh Patel2 years ago

@TrentonBricken 🙏

Owain Evans2 years ago

@TrentonBricken I discuss some slightly different arguments against the parrot framing here:

Grace2 years ago

@TrentonBricken I hadn’t heard the dehydration bit before 😮

Thirqual2 years ago

@StuartJRitchie @TrentonBricken Sure man, sure. Meanwhile chatGPT tells me: "The reason for listing "The Death of the Necromancer" before "The Element of Fire" is because "The Death of the Necromancer" was published first, in 1998, while "The Element of Fire" was published later, in 1993."

darren2 years ago

@TrentonBricken

Promptmetheus (COG/ACC)2 years ago

@TrentonBricken the whole 5 min clip of this portion was great

Name can't be blank2 years ago

@TrentonBricken I'm doubtful about the implied level of transfer learning. IIRC when you look at coarser meta-learning metrics for LLMs, they don't look so good. And transfer is hard even in humans.

evil malloc2 years ago

@TrentonBricken Has anyone really run ablations regarding this coding thing ? Something like two experiments with the same general corpus and with / w/o code leading to improvement in reasoning

Related Videos

Random Walks are not "just theory." They're one of the foundational models for decision-making under uncertainty. Robert Gallager's MIT lectures cover the full arc: Markov Processes → Random Walks → Hypothesis Testing → Thresholds. A pipeline that shows up everywhere: from stochastic modeling to signal detection to optimal stopping. This is the math your systems are built on. Know it.

Random Walks are not "just theory." They're one of the foundational models for decision-making under uncertainty. Robert Gallager's MIT lectures cover the full arc: Markov Processes → Random Walks → Hypothesis Testing → Thresholds. A pipeline that shows up everywhere: from stochastic modeling to signal detection to optimal stopping. This is the math your systems are built on. Know it.

Ruuj

17,336 views • 13 days ago

Sam on Kimi, distillation, and open source: “I have always assumed that there are going to be great cheap models in the world, and we better be the greatest and the cheapest. You get a better deal today, at least at a particular latency, using OpenAI's models than Kimi. We distill our own models. That’s how we make smaller, cheaper models. That’s a very good thing to do. There will clearly be an important place for open source models in the world and people that will want their own weights. We have so much usage of our models that we do not need to be a gigantically high-margin business to be able to afford model training. I would rather people not distill from us, for sure. But this is not in my top ten list of worries.”

Sam on Kimi, distillation, and open source: “I have always assumed that there are going to be great cheap models in the world, and we better be the greatest and the cheapest. You get a better deal today, at least at a particular latency, using OpenAI's models than Kimi. We distill our own models. That’s how we make smaller, cheaper models. That’s a very good thing to do. There will clearly be an important place for open source models in the world and people that will want their own weights. We have so much usage of our models that we do not need to be a gigantically high-margin business to be able to afford model training. I would rather people not distill from us, for sure. But this is not in my top ten list of worries.”

Patrick OShaughnessy

262,808 views • 2 days ago

Geoffrey Hinton explains that large language models are nothing like traditional software written line by line. Instead of explicit instructions, they rely on code that teaches them how to learn from data. What actually emerges is billions or trillions of learned connection strengths that no one can directly interpret. This makes their internal workings fundamentally opaque, much like the human brain.

Geoffrey Hinton explains that large language models are nothing like traditional software written line by line. Instead of explicit instructions, they rely on code that teaches them how to learn from data. What actually emerges is billions or trillions of learned connection strengths that no one can directly interpret. This makes their internal workings fundamentally opaque, much like the human brain.

Wes Roth

49,600 views • 6 months ago

Today we are introducing Tara. Biological datasets are a source of insights and a means to train biological AI models. As the ability to reason at scale emerges, they take on a new role: the ground truth for testing what reasoning models produce, and the environment in which those models operate, get feedback, and improve. Tara, our autonomous research agent, is embedded in our ever-expanding datasets, lab-generated and synthetic, and built to test and evolve the hypotheses frontier models generate, matching the pace at which they produce new ideas. By keeping those models grounded in a vast space of high-precision biological data, we believe we can compound biological reasoning and close the impedance mismatch between hypothesis generation and validation.

Today we are introducing Tara. Biological datasets are a source of insights and a means to train biological AI models. As the ability to reason at scale emerges, they take on a new role: the ground truth for testing what reasoning models produce, and the environment in which those models operate, get feedback, and improve. Tara, our autonomous research agent, is embedded in our ever-expanding datasets, lab-generated and synthetic, and built to test and evolve the hypotheses frontier models generate, matching the pace at which they produce new ideas. By keeping those models grounded in a vast space of high-precision biological data, we believe we can compound biological reasoning and close the impedance mismatch between hypothesis generation and validation.

Nima Alidoust

27,670 views • 1 month ago

𝐃𝐞𝐬𝐭𝐫𝐚 𝐎𝐂𝐀𝐈 (𝐎𝐧𝐞-𝐂𝐥𝐢𝐜𝐤 𝐀𝐈) 𝐌𝐨𝐝𝐞𝐥𝐬 - $DSYNC 𝐄𝐚𝐫𝐥𝐲 𝐀𝐜𝐜𝐞𝐬𝐬 𝐏𝐫𝐞𝐯𝐢𝐞𝐰 We are training and building a wide range of AI models for the Destra OCAI platform. Today, we will be showcasing an early preview of one of the initial models we are working on—a bullish/bearish prediction model designed to 𝐟𝐨𝐫𝐞𝐜𝐚𝐬𝐭 𝐭𝐡𝐞 𝐦𝐚𝐫𝐤𝐞𝐭 𝐝𝐢𝐫𝐞𝐜𝐭𝐢𝐨𝐧 𝐨𝐟 𝐬𝐩𝐞𝐜𝐢𝐟𝐢𝐜 𝐭𝐨𝐤𝐞𝐧𝐬. This is just one of the initial models we are working on; as we progress, the models will become more complex and intricate. In this behind-the-scenes video, we demonstrate how the model predicts the future market trend of the BTC-USD pair with an 𝐚𝐜𝐜𝐮𝐫𝐚𝐜𝐲 𝐨𝐟 𝟔𝟓%. This is the barebones structure of the models we are training, which will soon be available to users with a single click through the Destra OCAI platform. The OCAI platform includes a wide array of Destra Exclusive AI models, specifically designed to simplify life for crypto audiences, that are envisioned and built from scratch at Destra Labs.

𝐃𝐞𝐬𝐭𝐫𝐚 𝐎𝐂𝐀𝐈 (𝐎𝐧𝐞-𝐂𝐥𝐢𝐜𝐤 𝐀𝐈) 𝐌𝐨𝐝𝐞𝐥𝐬 - $DSYNC 𝐄𝐚𝐫𝐥𝐲 𝐀𝐜𝐜𝐞𝐬𝐬 𝐏𝐫𝐞𝐯𝐢𝐞𝐰 We are training and building a wide range of AI models for the Destra OCAI platform. Today, we will be showcasing an early preview of one of the initial models we are working on—a bullish/bearish prediction model designed to 𝐟𝐨𝐫𝐞𝐜𝐚𝐬𝐭 𝐭𝐡𝐞 𝐦𝐚𝐫𝐤𝐞𝐭 𝐝𝐢𝐫𝐞𝐜𝐭𝐢𝐨𝐧 𝐨𝐟 𝐬𝐩𝐞𝐜𝐢𝐟𝐢𝐜 𝐭𝐨𝐤𝐞𝐧𝐬. This is just one of the initial models we are working on; as we progress, the models will become more complex and intricate. In this behind-the-scenes video, we demonstrate how the model predicts the future market trend of the BTC-USD pair with an 𝐚𝐜𝐜𝐮𝐫𝐚𝐜𝐲 𝐨𝐟 𝟔𝟓%. This is the barebones structure of the models we are training, which will soon be available to users with a single click through the Destra OCAI platform. The OCAI platform includes a wide array of Destra Exclusive AI models, specifically designed to simplify life for crypto audiences, that are envisioned and built from scratch at Destra Labs.

Destra Network

37,135 views • 1 year ago

We are opening up the beta of our new AI writing tool to Exclusive Models. If you're exclusive to JFF, try it out and let us know your thoughts. At our Anniversary Conference, lots of models said they needed help making their posts more creative. This is a tool to help models take what they write and help them make better posts. Does this replace a human? No! In fact, if you are an erotic writer, apply to be in our Business Directory so models can hire you to help them out!

Sensitive content

We are opening up the beta of our new AI writing tool to Exclusive Models. If you're exclusive to JFF, try it out and let us know your thoughts. At our Anniversary Conference, lots of models said they needed help making their posts more creative. This is a tool to help models take what they write and help them make better posts. Does this replace a human? No! In fact, if you are an erotic writer, apply to be in our Business Directory so models can hire you to help them out!

JustForFans

15,325 views • 3 years ago

Small Language Models (SML) are the future of AI. "Small" (SML) instead of "Large" (LLM). These small models are highly specialized models with superhuman abilities on specific tasks. Here are two techniques to build these models: • Spectrum • Model Merging I give you a short introduction in the attached video, but here is a quick summary: Spectrum helps us identify the most relevant layers to solve one specific task. We can ignore everything else and focus on fine-tuning these layers. Using Spectrum, we can fine-tune models in a heartbeat. Model Merging combines multiple models into a unique, much better model than any of the individual input models. You can also combine models specialized in different tasks and get a model with multiple abilities. This is the state of the art of productizing models. It's what Arcee.ai's platform does behind the scenes. Arcee collaborated with me on this post and is sponsoring it. There are three main steps to produce a model for your particular use case: 1. You create a dataset by uploading your data. 2. You train a model. At this step, Arcee uses Spectrum and Model Merging to produce a highly specialized model for your task. 3. You can deploy that model to any environment you want. Three important notes: • Training process is 2x faster and 2x cheaper than regular fine-tuning. • Resultant models are smaller and have higher accuracy. • They create these specialized models from open-source models. Check this site so you can fully appreciate how this works: If you want to fine-tune an open-source model, consider Arcee's platform. This is the state of the art.

Small Language Models (SML) are the future of AI. "Small" (SML) instead of "Large" (LLM). These small models are highly specialized models with superhuman abilities on specific tasks. Here are two techniques to build these models: • Spectrum • Model Merging I give you a short introduction in the attached video, but here is a quick summary: Spectrum helps us identify the most relevant layers to solve one specific task. We can ignore everything else and focus on fine-tuning these layers. Using Spectrum, we can fine-tune models in a heartbeat. Model Merging combines multiple models into a unique, much better model than any of the individual input models. You can also combine models specialized in different tasks and get a model with multiple abilities. This is the state of the art of productizing models. It's what Arcee.ai's platform does behind the scenes. Arcee collaborated with me on this post and is sponsoring it. There are three main steps to produce a model for your particular use case: 1. You create a dataset by uploading your data. 2. You train a model. At this step, Arcee uses Spectrum and Model Merging to produce a highly specialized model for your task. 3. You can deploy that model to any environment you want. Three important notes: • Training process is 2x faster and 2x cheaper than regular fine-tuning. • Resultant models are smaller and have higher accuracy. • They create these specialized models from open-source models. Check this site so you can fully appreciate how this works: If you want to fine-tune an open-source model, consider Arcee's platform. This is the state of the art.

Santiago

164,162 views • 2 years ago

Today, we're joined by Yejin Choi, professor and senior fellow at Stanford University University in the Computer Science Department and Stanford UniversityHAI. In this conversation, we explore Yejin’s recent work on making small language models reason more effectively. We discuss how high-quality, diverse data plays a central role in closing the intelligence gap between small and large models, and how combining synthetic data generation, imitation learning, and reinforcement learning can unlock stronger reasoning capabilities in smaller models. Yejin explains the risks of homogeneity in model outputs and mode collapse highlighted in her “Artificial Hivemind” paper, and its impacts on human creativity and knowledge. We also discuss her team's novel approaches, including reinforcement learning as a pre-training objective, where models are incentivized to “think” before predicting the next token, and "Prismatic Synthesis," a gradient-based method for generating diverse synthetic math data while filtering overrepresented examples. Additionally, we cover the societal implications of AI and the concept of pluralistic alignment—ensuring AI reflects the diverse norms and values of humanity. Finally, Yejin shares her mission to democratize AI beyond large organizations and offers her predictions for the coming year. 🗒️ For the full list of resources for this episode, visit the show notes page: 📖 CHAPTERS =============================== 00:00 - Introduction 04:44 - "Snowball effect" in AI investments 06:58 - Approaches to smaller models 08:58 - Importance of “better data” 14:07 - Imitation learning 18:24 - Artificial Hivemind paper 25:25 - AI risks 27:50 - Spectrum tuning 28:53 - Future of AI on humanity 33:08 - Reasoning in small models 34:58 - Prismatic Synthesis 48:20 - Reinforcement as a Pretraining Objective 55:04 - Pluralistic alignment 1:03:30 - Predictions

Today, we're joined by Yejin Choi, professor and senior fellow at Stanford University University in the Computer Science Department and Stanford UniversityHAI. In this conversation, we explore Yejin’s recent work on making small language models reason more effectively. We discuss how high-quality, diverse data plays a central role in closing the intelligence gap between small and large models, and how combining synthetic data generation, imitation learning, and reinforcement learning can unlock stronger reasoning capabilities in smaller models. Yejin explains the risks of homogeneity in model outputs and mode collapse highlighted in her “Artificial Hivemind” paper, and its impacts on human creativity and knowledge. We also discuss her team's novel approaches, including reinforcement learning as a pre-training objective, where models are incentivized to “think” before predicting the next token, and "Prismatic Synthesis," a gradient-based method for generating diverse synthetic math data while filtering overrepresented examples. Additionally, we cover the societal implications of AI and the concept of pluralistic alignment—ensuring AI reflects the diverse norms and values of humanity. Finally, Yejin shares her mission to democratize AI beyond large organizations and offers her predictions for the coming year. 🗒️ For the full list of resources for this episode, visit the show notes page: 📖 CHAPTERS =============================== 00:00 - Introduction 04:44 - "Snowball effect" in AI investments 06:58 - Approaches to smaller models 08:58 - Importance of “better data” 14:07 - Imitation learning 18:24 - Artificial Hivemind paper 25:25 - AI risks 27:50 - Spectrum tuning 28:53 - Future of AI on humanity 33:08 - Reasoning in small models 34:58 - Prismatic Synthesis 48:20 - Reinforcement as a Pretraining Objective 55:04 - Pluralistic alignment 1:03:30 - Predictions

The TWIML AI Podcast

12,141 views • 6 months ago

3D-LLM: Injecting the 3D World into Large Language Models paper page: Large language models (LLMs) and Vision-Language Models (VLMs) have been proven to excel at multiple tasks, such as commonsense reasoning. Powerful as these models can be, they are not grounded in the 3D physical world, which involves richer concepts such as spatial relationships, affordances, physics, layout, and so on. In this work, we propose to inject the 3D world into large language models and introduce a whole new family of 3D-LLMs. Specifically, 3D-LLMs can take 3D point clouds and their features as input and perform a diverse set of 3D-related tasks, including captioning, dense captioning, 3D question answering, task decomposition, 3D grounding, 3D-assisted dialog, navigation, and so on. Using three types of prompting mechanisms that we design, we are able to collect over 300k 3D-language data covering these tasks. To efficiently train 3D-LLMs, we first utilize a 3D feature extractor that obtains 3D features from rendered multi- view images. Then, we use 2D VLMs as our backbones to train our 3D-LLMs. By introducing a 3D localization mechanism, 3D-LLMs can better capture 3D spatial information. Experiments on ScanQA show that our model outperforms state-of-the-art baselines by a large margin (e.g., the BLEU-1 score surpasses state-of-the-art score by 9%). Furthermore, experiments on our held-in datasets for 3D captioning, task composition, and 3D-assisted dialogue show that our model outperforms 2D VLMs. Qualitative examples also show that our model could perform more tasks beyond the scope of existing LLMs and VLMs.

3D-LLM: Injecting the 3D World into Large Language Models paper page: Large language models (LLMs) and Vision-Language Models (VLMs) have been proven to excel at multiple tasks, such as commonsense reasoning. Powerful as these models can be, they are not grounded in the 3D physical world, which involves richer concepts such as spatial relationships, affordances, physics, layout, and so on. In this work, we propose to inject the 3D world into large language models and introduce a whole new family of 3D-LLMs. Specifically, 3D-LLMs can take 3D point clouds and their features as input and perform a diverse set of 3D-related tasks, including captioning, dense captioning, 3D question answering, task decomposition, 3D grounding, 3D-assisted dialog, navigation, and so on. Using three types of prompting mechanisms that we design, we are able to collect over 300k 3D-language data covering these tasks. To efficiently train 3D-LLMs, we first utilize a 3D feature extractor that obtains 3D features from rendered multi- view images. Then, we use 2D VLMs as our backbones to train our 3D-LLMs. By introducing a 3D localization mechanism, 3D-LLMs can better capture 3D spatial information. Experiments on ScanQA show that our model outperforms state-of-the-art baselines by a large margin (e.g., the BLEU-1 score surpasses state-of-the-art score by 9%). Furthermore, experiments on our held-in datasets for 3D captioning, task composition, and 3D-assisted dialogue show that our model outperforms 2D VLMs. Qualitative examples also show that our model could perform more tasks beyond the scope of existing LLMs and VLMs.

AK

249,708 views • 3 years ago

Professor Judea Pearl — the pioneer who invented causal reasoning in AI — says scaling won't save us. "Mathematical limitations that are not crossable by scaling up." The brutal truth: LLMs aren’t learning how the world works. They are learning how we describe the world. This resonates with most biologists: Drug discovery is hitting the same wall. We have mountains of genomic data, but most AI models just find patterns in published papers — not in the raw biology itself. They're learning what scientists think causes disease, not what actually does. Pearl's causal revolution? That's how we move from "this gene correlates with cancer" to "this gene causes cancer" — and finally design drugs that work. Until then, we're building very expensive parrots.

Professor Judea Pearl — the pioneer who invented causal reasoning in AI — says scaling won't save us. "Mathematical limitations that are not crossable by scaling up." The brutal truth: LLMs aren’t learning how the world works. They are learning how we describe the world. This resonates with most biologists: Drug discovery is hitting the same wall. We have mountains of genomic data, but most AI models just find patterns in published papers — not in the raw biology itself. They're learning what scientists think causes disease, not what actually does. Pearl's causal revolution? That's how we move from "this gene correlates with cancer" to "this gene causes cancer" — and finally design drugs that work. Until then, we're building very expensive parrots.

Bo Wang

803,230 views • 5 months ago

At Cohere we deploy our models directly to our customers, instead of them sending data to us. It makes our job harder, but their business more secure: “When you’re using a consumer app, they are using the data you’re putting in there, training on it, all the time” - Nick Frosst

At Cohere we deploy our models directly to our customers, instead of them sending data to us. It makes our job harder, but their business more secure: “When you’re using a consumer app, they are using the data you’re putting in there, training on it, all the time” - Nick Frosst

Cohere

10,460 views • 27 days ago

BullshitBench v2 is out! It is one of the few benchmarks where models are generally not getting better (except Claude) and where reasoning isn't helping. What's new: 100 new questions, by domain (coding (40 Q's), medical (15), legal (15), finance (15), physics(15)), 70+ model variants tested. BullshitBench is already at 380 starts on GitHub - all questions, scripts, responses and judgements are there so check it out. TL;DR: - Results replicated - Anthropic latest models are scoring exceptionally well - Qwen is another very strong performer - OpenAI and Google models are not doing well and are not improving - Domains do not show much difference - rates of BS detection are about the same across all domains - Reasoning, if anything, has negative effect - Newer models don't do that much better than older ones (except Anthropic) Links: - Data explorer: - GitHub: Highly recommend the data explorer where you can study the data and the questions & sample answers.

BullshitBench v2 is out! It is one of the few benchmarks where models are generally not getting better (except Claude) and where reasoning isn't helping. What's new: 100 new questions, by domain (coding (40 Q's), medical (15), legal (15), finance (15), physics(15)), 70+ model variants tested. BullshitBench is already at 380 starts on GitHub - all questions, scripts, responses and judgements are there so check it out. TL;DR: - Results replicated - Anthropic latest models are scoring exceptionally well - Qwen is another very strong performer - OpenAI and Google models are not doing well and are not improving - Domains do not show much difference - rates of BS detection are about the same across all domains - Reasoning, if anything, has negative effect - Newer models don't do that much better than older ones (except Anthropic) Links: - Data explorer: - GitHub: Highly recommend the data explorer where you can study the data and the questions & sample answers.

Peter Gostev

239,209 views • 5 months ago

Demis on why world models are his longest standing passion and explains benefits vs. language models: ▫️ “I think language models are able to understand a lot about the world. More than we expected because language is actually probably richer than we thought. But there's still a lot about the spatial dynamics of the world, spatial awareness and the physical context we're in — and how that works mechanically — that is hard to describe in words and isn't generally described in corpuses of words. Alot of this is allied to learning from experience. There's a lot of things which you can't really describe something. You have to just experience it. Maybe the senses and so on are very hard to put into words. Whether that's motor angles and smell and these kinds of senses, it's very difficult to describe that in any kind of language.”▫️

Demis on why world models are his longest standing passion and explains benefits vs. language models: ▫️ “I think language models are able to understand a lot about the world. More than we expected because language is actually probably richer than we thought. But there's still a lot about the spatial dynamics of the world, spatial awareness and the physical context we're in — and how that works mechanically — that is hard to describe in words and isn't generally described in corpuses of words. Alot of this is allied to learning from experience. There's a lot of things which you can't really describe something. You have to just experience it. Maybe the senses and so on are very hard to put into words. Whether that's motor angles and smell and these kinds of senses, it's very difficult to describe that in any kind of language.”▫️

Bearly AI

78,545 views • 2 months ago

Exa CEO Will Bryk explains why retrieval can help solve the tokenpocalypse: "We should not be using gigantic models for every task." "You should use a family of models of different sizes. The big model decides what to do, and it dishes out commands to the small models, and those small models can be way more accurate and reliable if they're using retrieval." "Retrieval helps small models act like big models... We do save our customers a huge amount of tokens because they can use smaller models and use retrieval." "We could save 20x on cost for customers compared to other providers by being very efficient in what information from the web the agent actually sees." Will Bryk with Sarah Wang

Exa CEO Will Bryk explains why retrieval can help solve the tokenpocalypse: "We should not be using gigantic models for every task." "You should use a family of models of different sizes. The big model decides what to do, and it dishes out commands to the small models, and those small models can be way more accurate and reliable if they're using retrieval." "Retrieval helps small models act like big models... We do save our customers a huge amount of tokens because they can use smaller models and use retrieval." "We could save 20x on cost for customers compared to other providers by being very efficient in what information from the web the agent actually sees." Will Bryk with Sarah Wang

a16z

25,144 views • 1 month ago

World models — action-conditioned predictive models of the environment — are an exciting are of research for robots that can be useful both for training and for test-time compute. But video-based world models waste a lot of predictive power on reconstructing pixels, which makes model and data requirements much higher and limits how far out into the future their predictions remain viable. Instead, what if we learned a purely semantic world model, one which predicts which properties will be true about the world after a sequence of actions, without reconstructing the whole images? Jacob Berg tells us more. Watch Episode #53 of RoboPapers now, with Michael Cho - Rbt/Acc and Chris Paxton!

World models — action-conditioned predictive models of the environment — are an exciting are of research for robots that can be useful both for training and for test-time compute. But video-based world models waste a lot of predictive power on reconstructing pixels, which makes model and data requirements much higher and limits how far out into the future their predictions remain viable. Instead, what if we learned a purely semantic world model, one which predicts which properties will be true about the world after a sequence of actions, without reconstructing the whole images? Jacob Berg tells us more. Watch Episode #53 of RoboPapers now, with Michael Cho - Rbt/Acc and Chris Paxton!

RoboPapers

39,322 views • 7 months ago

Introducing Reinforcement-Learned Teachers (RLTs): Transforming how we teach LLMs to reason with reinforcement learning (RL). Blog: Paper: Traditional RL focuses on “learning to solve” challenging problems with expensive LLMs and constitutes a key step in making student AI systems ultimately acquire reasoning capabilities via distillation and cold-starting. Enter our RLTs—a new class of models prompted with not only a problem’s question but also its solution, and directly trained to generate clear, step-by-step “explanations” to teach their students. Remarkably, an RLT with only 7B parameters produces superior results when distilling and cold-starting students in competitive and graduate-level reasoning tasks than orders-of-magnitude larger LLMs. RLTs are as effective even when distilling 32B students, much larger than the teacher itself—unlocking a new standard for efficiency in developing reasoning language models with RL. Code:

Introducing Reinforcement-Learned Teachers (RLTs): Transforming how we teach LLMs to reason with reinforcement learning (RL). Blog: Paper: Traditional RL focuses on “learning to solve” challenging problems with expensive LLMs and constitutes a key step in making student AI systems ultimately acquire reasoning capabilities via distillation and cold-starting. Enter our RLTs—a new class of models prompted with not only a problem’s question but also its solution, and directly trained to generate clear, step-by-step “explanations” to teach their students. Remarkably, an RLT with only 7B parameters produces superior results when distilling and cold-starting students in competitive and graduate-level reasoning tasks than orders-of-magnitude larger LLMs. RLTs are as effective even when distilling 32B students, much larger than the teacher itself—unlocking a new standard for efficiency in developing reasoning language models with RL. Code:

Sakana AI

179,276 views • 1 year ago

Earlier this week at GTC, we announced our partnership with Nvidia. We will work with Nvidia to build strong, American open-source models that are at the frontier of scientific reasoning. These models will be essential for the US to compete with China on science in the coming decades. Jensen is committing to spend tens of billions of dollars developing open-source models, and we are excited to be a partner with them in figuring out how to benchmark, train and use those agents to accelerate scientific research. We have already open-sourced some of the work we have done with them, and are looking forward to open-sourcing more. There are few things today that are more important. See our blog post below, and watch the video to learn more, narrated by the man himself.

Earlier this week at GTC, we announced our partnership with Nvidia. We will work with Nvidia to build strong, American open-source models that are at the frontier of scientific reasoning. These models will be essential for the US to compete with China on science in the coming decades. Jensen is committing to spend tens of billions of dollars developing open-source models, and we are excited to be a partner with them in figuring out how to benchmark, train and use those agents to accelerate scientific research. We have already open-sourced some of the work we have done with them, and are looking forward to open-sourcing more. There are few things today that are more important. See our blog post below, and watch the video to learn more, narrated by the man himself.

Sam Rodriques

23,516 views • 4 months ago

Demis Hassabis says world models are his longest standing passion and explains benefits vs. language models: ▫️ “I think language models are able to understand a lot about the world. More than we expected because language is actually probably richer than we thought. But there's still a lot about the spatial dynamics of the world, spatial awareness and the physical context we're in — and how that works mechanically — that is hard to describe in words and isn't generally described in corpuses of words. Alot of this is allied to learning from experience. There's a lot of things which you can't really describe something. You have to just experience it. Maybe the senses and so on are very hard to put into words. Whether that's motor angles and smell and these kinds of senses, it's very difficult to describe that in any kind of language.”▫️ This is what Demis and Google Deepmind is trying to solve with Genie. He also says that the video models (Veo) will play a part in training the world models and this is all key for AI robotics.

Demis Hassabis says world models are his longest standing passion and explains benefits vs. language models: ▫️ “I think language models are able to understand a lot about the world. More than we expected because language is actually probably richer than we thought. But there's still a lot about the spatial dynamics of the world, spatial awareness and the physical context we're in — and how that works mechanically — that is hard to describe in words and isn't generally described in corpuses of words. Alot of this is allied to learning from experience. There's a lot of things which you can't really describe something. You have to just experience it. Maybe the senses and so on are very hard to put into words. Whether that's motor angles and smell and these kinds of senses, it's very difficult to describe that in any kind of language.”▫️ This is what Demis and Google Deepmind is trying to solve with Genie. He also says that the video models (Veo) will play a part in training the world models and this is all key for AI robotics.

Bearly AI

123,703 views • 7 months ago

Revolutionizing Move Programming with OpenLedger In this demo, we showcase how Move datasets contributed by data providers to OpenLedger’s datanets are used to fine-tune specialized models with LoRA fine-tuning. As seen in the video, we showcase an example on how builders can deploy a Move-specialized model that powers Co-pilot agents using our no-code model fine-tuning platform. This is the future of AI and Web3 innovation. Watch this space to see more specialised models and data feeds being built for next generation agents on top of OpenLedger #Move

Revolutionizing Move Programming with OpenLedger In this demo, we showcase how Move datasets contributed by data providers to OpenLedger’s datanets are used to fine-tune specialized models with LoRA fine-tuning. As seen in the video, we showcase an example on how builders can deploy a Move-specialized model that powers Co-pilot agents using our no-code model fine-tuning platform. This is the future of AI and Web3 innovation. Watch this space to see more specialised models and data feeds being built for next generation agents on top of OpenLedger #Move

OpenLedger

61,662 views • 1 year ago