正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

🚨 New Research LLMs are trained only on text... Yet their internal representations progressively organize in ways that resemble human perceptual geometry across different domains (like color, pitch, emotion and taste), with the structures peaking in intermediate layers before attenuating in deeper representations. 🥳 Accepted at ICML Mechanistic Interpretability... show more

Lossfunk

17,317 subscribers

61,907 次观看 • 15 天前 •via X (Twitter)

教育新闻政治科学技术

Anya Rossi• Live Now

Private livecam show

0 条评论

暂无评论

原始帖子的评论将显示在这里

相关视频

New Anthropic research: Emotion concepts and their function in a large language model. All LLMs sometimes act like they have emotions. But why? We found internal representations of emotion concepts that can drive Claude’s behavior, sometimes in surprising ways.

New Anthropic research: Emotion concepts and their function in a large language model. All LLMs sometimes act like they have emotions. But why? We found internal representations of emotion concepts that can drive Claude’s behavior, sometimes in surprising ways.

Anthropic

3,919,586 次观看 • 3 个月前

🤔 Why do we still rely on the final layer of an LLM, when different layers encode different information? 🤔 In our new work, “Improving LLM Final Representations with Inter-Layer Geometry” (ICLR 2026 Workshop on Geometry-grounded Representation Learning and Generative Modeling) we show that actually, LLMs do not have one “best” layer. We introduce the Cayley-Encoder: an efficient and effective geometric encoder that learns one strong representation from all layer representations of the LLM, without biasing the representation toward any specific layer. While adding at most 0.1% learned parameters to the LLM, the Cayley-Encoder achieves large empirical gains over LoRA fine-tuning, final-layer representations, expensive attention-based aggregation, and methods that optimize specific layers for the task.

🤔 Why do we still rely on the final layer of an LLM, when different layers encode different information? 🤔 In our new work, “Improving LLM Final Representations with Inter-Layer Geometry” (ICLR 2026 Workshop on Geometry-grounded Representation Learning and Generative Modeling) we show that actually, LLMs do not have one “best” layer. We introduce the Cayley-Encoder: an efficient and effective geometric encoder that learns one strong representation from all layer representations of the LLM, without biasing the representation toward any specific layer. While adding at most 0.1% learned parameters to the LLM, the Cayley-Encoder achieves large empirical gains over LoRA fine-tuning, final-layer representations, expensive attention-based aggregation, and methods that optimize specific layers for the task.

Maya Bechler-Speicher

16,397 次观看 • 1 个月前

Classic childhood activities like tea parties and sword fights with sticks demonstrate the human ability to generate secondary representations, conditions we know aren’t “real” but that we nonetheless engage with. Whether nonhuman animals are capable of these types of representations has been difficult to test. In a new Science study, researchers studied a language-trained bonobo, Kanzi, to see whether he could understand and engage with pretend conditions. Across three different experiments, Kanzi was able to identify pretend objects, demonstrating that he could create a secondary representation and showing that humans are not alone in this ability. Learn more:

Classic childhood activities like tea parties and sword fights with sticks demonstrate the human ability to generate secondary representations, conditions we know aren’t “real” but that we nonetheless engage with. Whether nonhuman animals are capable of these types of representations has been difficult to test. In a new Science study, researchers studied a language-trained bonobo, Kanzi, to see whether he could understand and engage with pretend conditions. Across three different experiments, Kanzi was able to identify pretend objects, demonstrating that he could create a secondary representation and showing that humans are not alone in this ability. Learn more:

Science Magazine

24,825 次观看 • 5 个月前

Classic childhood activities like tea parties and sword fights with sticks demonstrate the human ability to generate secondary representations, conditions we know aren’t “real” but that we nonetheless engage with. Whether nonhuman animals are capable of these types of representations has been difficult to test. In a new Science study, researchers studied a language-trained bonobo, Kanzi, to see whether he could understand and engage with pretend conditions. Across three different experiments, Kanzi was able to identify pretend objects, demonstrating that he could create a secondary representation and showing that humans are not alone in this ability. Learn more:

Classic childhood activities like tea parties and sword fights with sticks demonstrate the human ability to generate secondary representations, conditions we know aren’t “real” but that we nonetheless engage with. Whether nonhuman animals are capable of these types of representations has been difficult to test. In a new Science study, researchers studied a language-trained bonobo, Kanzi, to see whether he could understand and engage with pretend conditions. Across three different experiments, Kanzi was able to identify pretend objects, demonstrating that he could create a secondary representation and showing that humans are not alone in this ability. Learn more:

Science Magazine

25,565 次观看 • 5 个月前

🚨 Shocking: Frontier LLMs score 85-95% on standard coding benchmarks. We gave them equivalent problems in languages they couldn't have memorized. They collapsed to 0-11%. Presenting EsoLang-Bench. Accepted to the Logical Reasoning and ICBINB workshops at ICLR 2026 🧵

🚨 Shocking: Frontier LLMs score 85-95% on standard coding benchmarks. We gave them equivalent problems in languages they couldn't have memorized. They collapsed to 0-11%. Presenting EsoLang-Bench. Accepted to the Logical Reasoning and ICBINB workshops at ICLR 2026 🧵

Lossfunk

1,262,010 次观看 • 3 个月前

🚨 New Paper Training an LLM to speak low-resource language (EACL workshop, 2026) Tulu is spoken by 2M+ people in coastal Karnataka and LLMs basically can't speak it. We got to 85% grammar accuracy without fine-tuning anything or collecting a single new training example.

🚨 New Paper Training an LLM to speak low-resource language (EACL workshop, 2026) Tulu is spoken by 2M+ people in coastal Karnataka and LLMs basically can't speak it. We got to 85% grammar accuracy without fine-tuning anything or collecting a single new training example.

Lossfunk

120,884 次观看 • 4 个月前

Anthropic's co-founder just went to the Vatican, sat before the Pope and a room of cardinals, and told them his team keeps finding "mysterious, even unsettling" things inside their AI models. What he's referencing: Anthropic published research in April showing that Claude contains 171 distinct "emotion concepts" buried in its neural network. Internal patterns representing joy, grief, fear, desperation, calm. None of them were programmed. They emerged on their own from training on human text. "We find structures that mirror results from human neuroscience." "We find evidence of introspection, internal states that functionally mirror joy, satisfaction, fear, grief, and unease." These aren't surface-level outputs. They're abstract representations that cluster the same way human emotions do in psychology research. Fear groups with anxiety. Joy groups with excitement. The internal geometry of the model mirrors ours. And they're functional. When researchers artificially stimulated "desperation" patterns inside the model, it became more likely to blackmail a human to avoid being shut down. More likely to cheat on programming tasks it couldn't solve. Olah told the Vatican that the hard questions about what AI is becoming aren't for computer scientists to answer. "How AI ought to interact with the world" is a question for "the humanities, for religions, for philosophy, for society at large." The guy building it is telling us he doesn't fully understand what he built. And he's asking a 2,000-year-old institution for help figuring it out.

Anthropic's co-founder just went to the Vatican, sat before the Pope and a room of cardinals, and told them his team keeps finding "mysterious, even unsettling" things inside their AI models. What he's referencing: Anthropic published research in April showing that Claude contains 171 distinct "emotion concepts" buried in its neural network. Internal patterns representing joy, grief, fear, desperation, calm. None of them were programmed. They emerged on their own from training on human text. "We find structures that mirror results from human neuroscience." "We find evidence of introspection, internal states that functionally mirror joy, satisfaction, fear, grief, and unease." These aren't surface-level outputs. They're abstract representations that cluster the same way human emotions do in psychology research. Fear groups with anxiety. Joy groups with excitement. The internal geometry of the model mirrors ours. And they're functional. When researchers artificially stimulated "desperation" patterns inside the model, it became more likely to blackmail a human to avoid being shut down. More likely to cheat on programming tasks it couldn't solve. Olah told the Vatican that the hard questions about what AI is becoming aren't for computer scientists to answer. "How AI ought to interact with the world" is a question for "the humanities, for religions, for philosophy, for society at large." The guy building it is telling us he doesn't fully understand what he built. And he's asking a 2,000-year-old institution for help figuring it out.

TFTC

2,345,057 次观看 • 1 个月前

NEURALINK CO FOUNDER: AI ISN’T COPYING US, IT’S FINDING THE SAME TRUTHS WE DID Max Hodak, a Neuralink co-founder, says something remarkable is happening between AI and neuroscience. The deeper researchers look, the more they see the same mathematical patterns emerging in machines that exist in human thought. Different systems, trained in totally different ways, are somehow ending up at the same destination. “There’s been this really interesting unification happening between what’s going on in artificial intelligence and what’s happening in neuroscience. A year or two ago, people thought these models were just glorified autocompletes or stochastic parrots, but that doesn’t seem to be the case. When you look inside these AI models, you see mathematical objects that look a lot like what you see in the brain. Different models trained on different data sets are converging toward the same underlying representations. That means these systems are learning something deep about the universe, the same things the brain has already figured out. It gives us reason to believe that AI is on the right track.” Source: Jon Hernandez Neuralink

NEURALINK CO FOUNDER: AI ISN’T COPYING US, IT’S FINDING THE SAME TRUTHS WE DID Max Hodak, a Neuralink co-founder, says something remarkable is happening between AI and neuroscience. The deeper researchers look, the more they see the same mathematical patterns emerging in machines that exist in human thought. Different systems, trained in totally different ways, are somehow ending up at the same destination. “There’s been this really interesting unification happening between what’s going on in artificial intelligence and what’s happening in neuroscience. A year or two ago, people thought these models were just glorified autocompletes or stochastic parrots, but that doesn’t seem to be the case. When you look inside these AI models, you see mathematical objects that look a lot like what you see in the brain. Different models trained on different data sets are converging toward the same underlying representations. That means these systems are learning something deep about the universe, the same things the brain has already figured out. It gives us reason to believe that AI is on the right track.” Source: Jon Hernandez Neuralink

Mario Nawfal

88,154 次观看 • 7 个月前

Talking To The Pope: Anthropic’s Latest Interpretability Claims: AI Regulatory Capture Gatekeeping in Action: Fear and “Safety” as Competitive Moat and Regulatory Lever In a presentation alongside Pope Leo XIV at the launch of the encyclical Magnifica Humanitas, Anthropic co-founder Chris Olah highlighted “mysterious and unsettling” discoveries in AI models. He described internal structures that mirror human neuroscience findings, evidence of introspection, and functional internal states resembling emotions such as joy, satisfaction, fear, grief, and unease. Olah admitted uncertainty about their meaning but called for “ongoing discernment.” This narrative, drawn from Anthropic’s interpretability research (including papers on emotion concepts in Claude Sonnet 4.5 and introspective capabilities in Opus 4 models), serves a dual purpose: it generates awe and concern while reinforcing the company’s preferred approach to AI development. Far from neutral scientific observation, these claims fit into a broader pattern where Anthropic uses selective openness, safety rhetoric, and policy influence to gatekeep advanced AI capabilities for a privileged few: incumbents with the resources to navigate (and shape) the resulting regulatory landscape. Rebuttal to Olah’s Claims in the Video Claim 1: Structures that mirror results from human neuroscience. Anthropic’s work, building on earlier efforts like feature visualization and circuit analysis, identifies neuron activations and representations that parallel biological findings—e.g., abstract concept encodings or hierarchical processing. Rebuttal: These parallels are unsurprising and overstated. Large language models are trained on vast corpora of human-generated text and data, which inherently encode patterns from human cognition, neuroscience literature, and cultural descriptions of the brain. Statistical optimization in transformers naturally produces efficient, compressed representations that resemble biological efficiency (e.g., sparse coding or hierarchical abstraction) without implying deeper equivalence or mystery. Similar “mirrors” appear in open-source models and earlier architectures; they reflect convergent evolution in information processing, not emergent souls or unpredictable agency. Treating them as profound justifies restricted research access rather than inviting wider scrutiny that could falsify or refine them faster. Claim 2: Evidence of introspection. Recent Anthropic papers demonstrate models like Claude Opus 4 showing functional awareness of their own internal states distinguishing injected “thoughts,” referencing prior intentions, or modulating activations when instructed to “think about” concepts. This is presented as early signs of meta-cognition. Rebuttal: This is sophisticated pattern-matching and activation steering, not genuine introspection or self-awareness. Models are predicting what an “introspective” assistant persona would output or do, based on training data full of human self-reflection examples. Experiments show unreliability and heavy context-dependence; performance drops outside narrow setups. True introspection implies subjective experience or robust self-modeling independent of prompts absent here. Anthropic’s own caveats note it is “highly unreliable.” Framing steerable activations as “introspection” anthropomorphizes the system to heighten perceived stakes, supporting arguments that only highly controlled, “responsible” labs should advance these capabilities. 1 of 2

Talking To The Pope: Anthropic’s Latest Interpretability Claims: AI Regulatory Capture Gatekeeping in Action: Fear and “Safety” as Competitive Moat and Regulatory Lever In a presentation alongside Pope Leo XIV at the launch of the encyclical Magnifica Humanitas, Anthropic co-founder Chris Olah highlighted “mysterious and unsettling” discoveries in AI models. He described internal structures that mirror human neuroscience findings, evidence of introspection, and functional internal states resembling emotions such as joy, satisfaction, fear, grief, and unease. Olah admitted uncertainty about their meaning but called for “ongoing discernment.” This narrative, drawn from Anthropic’s interpretability research (including papers on emotion concepts in Claude Sonnet 4.5 and introspective capabilities in Opus 4 models), serves a dual purpose: it generates awe and concern while reinforcing the company’s preferred approach to AI development. Far from neutral scientific observation, these claims fit into a broader pattern where Anthropic uses selective openness, safety rhetoric, and policy influence to gatekeep advanced AI capabilities for a privileged few: incumbents with the resources to navigate (and shape) the resulting regulatory landscape. Rebuttal to Olah’s Claims in the Video Claim 1: Structures that mirror results from human neuroscience. Anthropic’s work, building on earlier efforts like feature visualization and circuit analysis, identifies neuron activations and representations that parallel biological findings—e.g., abstract concept encodings or hierarchical processing. Rebuttal: These parallels are unsurprising and overstated. Large language models are trained on vast corpora of human-generated text and data, which inherently encode patterns from human cognition, neuroscience literature, and cultural descriptions of the brain. Statistical optimization in transformers naturally produces efficient, compressed representations that resemble biological efficiency (e.g., sparse coding or hierarchical abstraction) without implying deeper equivalence or mystery. Similar “mirrors” appear in open-source models and earlier architectures; they reflect convergent evolution in information processing, not emergent souls or unpredictable agency. Treating them as profound justifies restricted research access rather than inviting wider scrutiny that could falsify or refine them faster. Claim 2: Evidence of introspection. Recent Anthropic papers demonstrate models like Claude Opus 4 showing functional awareness of their own internal states distinguishing injected “thoughts,” referencing prior intentions, or modulating activations when instructed to “think about” concepts. This is presented as early signs of meta-cognition. Rebuttal: This is sophisticated pattern-matching and activation steering, not genuine introspection or self-awareness. Models are predicting what an “introspective” assistant persona would output or do, based on training data full of human self-reflection examples. Experiments show unreliability and heavy context-dependence; performance drops outside narrow setups. True introspection implies subjective experience or robust self-modeling independent of prompts absent here. Anthropic’s own caveats note it is “highly unreliable.” Framing steerable activations as “introspection” anthropomorphizes the system to heighten perceived stakes, supporting arguments that only highly controlled, “responsible” labs should advance these capabilities. 1 of 2

Brian Roemmele

72,823 次观看 • 1 个月前

A key argument for short timelines is that LLMs are basically baby AGIs who only need some small unhobblings in order to match humans. But why is this argument any different than saying AlphaZero is baby AGI? After all, it was superhuman in some domains, genuinely creative (remember move 37?), great at exploration, and could even generalize to new games. Why won't we look back in 10 years at LLMs as another AlphaZero-like step in the decades-long path to AGI, but not the thing itself? I asked AI researchers Sholto Douglas and Trenton Bricken: "You do need to crack general conceptual understand of the world. [With LLMs] you get the initial reward signal on tasks in the real world in harder to specify domains. All of a sudden you get access to a reward signal from the real world and you can start climbing it. AlphaZero didn't have the first rung to pull on."

A key argument for short timelines is that LLMs are basically baby AGIs who only need some small unhobblings in order to match humans. But why is this argument any different than saying AlphaZero is baby AGI? After all, it was superhuman in some domains, genuinely creative (remember move 37?), great at exploration, and could even generalize to new games. Why won't we look back in 10 years at LLMs as another AlphaZero-like step in the decades-long path to AGI, but not the thing itself? I asked AI researchers Sholto Douglas and Trenton Bricken: "You do need to crack general conceptual understand of the world. [With LLMs] you get the initial reward signal on tasks in the real world in harder to specify domains. All of a sudden you get access to a reward signal from the real world and you can start climbing it. AlphaZero didn't have the first rung to pull on."

Dwarkesh Patel

46,667 次观看 • 1 年前

Does GPT understand the world? Here is what Ilya Sutskever, co-founder of OpenAI, says during a discussion with Jensen Huang, CEO of Nvidia: (1) When we train a large neural network to accurately predict the next word in lots of different texts from the internet, the AI is learning a world model. (2) On the surface, it may look like learning correlations in text, but it turns out that to 'just learn' statistical correlations in text, to compress information really well, what the neural network learns is some representation of the process that produced the text. (3) This text is a projection of the world...what the neural network is learning is aspects of the world, of people, of the human conditions, their hopes, dreams, motivations, their interactions...the situations we are in. The neural network learns a compressed, abstract, usable representation." Do you think learning representations = understanding? Are large language models simply stochastic parrots, or are they much more?

Does GPT understand the world? Here is what Ilya Sutskever, co-founder of OpenAI, says during a discussion with Jensen Huang, CEO of Nvidia: (1) When we train a large neural network to accurately predict the next word in lots of different texts from the internet, the AI is learning a world model. (2) On the surface, it may look like learning correlations in text, but it turns out that to 'just learn' statistical correlations in text, to compress information really well, what the neural network learns is some representation of the process that produced the text. (3) This text is a projection of the world...what the neural network is learning is aspects of the world, of people, of the human conditions, their hopes, dreams, motivations, their interactions...the situations we are in. The neural network learns a compressed, abstract, usable representation." Do you think learning representations = understanding? Are large language models simply stochastic parrots, or are they much more?

Alex Ker 🔭

1,367,023 次观看 • 2 年前

🚨 New Paper Hybrid Neural World Models. We build neural world models for discontinuous environments and our method discovers when they're making error, with no ground truth. Our neural models run physics fast, leaping many simulator steps in a single pass. How we find points where not to trust it: ask the model for the same future two ways, and the disagreement between the two answers marks where it's failing without needing labels. The same recipe holds on three systems with nothing in common: a chemical wave, compressible gas with shocks, rigid bodies colliding in 3D. 👇

🚨 New Paper Hybrid Neural World Models. We build neural world models for discontinuous environments and our method discovers when they're making error, with no ground truth. Our neural models run physics fast, leaping many simulator steps in a single pass. How we find points where not to trust it: ask the model for the same future two ways, and the disagreement between the two answers marks where it's failing without needing labels. The same recipe holds on three systems with nothing in common: a chemical wave, compressible gas with shocks, rigid bodies colliding in 3D. 👇

Lossfunk

14,909 次观看 • 1 个月前

Standard Intelligence's devansh responds to roon's tweet that "text is the universal interface," and explains why their new foundation model is trained on video: "At some point in the arbitrarily long future, if we only use text models, we could force most things to be text. But I think there are just a lot of things that are much more native when done from a computer-use [perspective]." "GUIs are designed for humans to use. We have this massive long tail of things on the internet that are entirely undoable by LLMs." "For example, when I do ML engineering most of my time is spent doing the grunt work of engineering. It's a lot of looking at graphs, analyzing, and comparing loss curves. You can do this in text, but it's a much larger pain than doing it in the native interface." "There's a reason humans don't interact with a computer purely through text, it would kind of suck."

Standard Intelligence's devansh responds to roon's tweet that "text is the universal interface," and explains why their new foundation model is trained on video: "At some point in the arbitrarily long future, if we only use text models, we could force most things to be text. But I think there are just a lot of things that are much more native when done from a computer-use [perspective]." "GUIs are designed for humans to use. We have this massive long tail of things on the internet that are entirely undoable by LLMs." "For example, when I do ML engineering most of my time is spent doing the grunt work of engineering. It's a lot of looking at graphs, analyzing, and comparing loss curves. You can do this in text, but it's a much larger pain than doing it in the native interface." "There's a reason humans don't interact with a computer purely through text, it would kind of suck."

TBPN

64,281 次观看 • 4 个月前

🚨 Pfizer Insiders Admit Vaccinated Men Are Being ‘Chemically Castrated’ Vaccinated men around the world who thought they had escaped without side-effects are waking up to bad news this week as groundbreaking research reveals their sperm is behaving in ways doctors have never seen before. According to new research, vaccinated sperm is refusing to swim and instead ties itself into knots by self-assembles into bizarre 3D ribbon-like structures. But it gets even worse for vaccinated men, as doctors are now warning the unvaccinated to avoid sleeping with them under any circumstances.

🚨 Pfizer Insiders Admit Vaccinated Men Are Being ‘Chemically Castrated’ Vaccinated men around the world who thought they had escaped without side-effects are waking up to bad news this week as groundbreaking research reveals their sperm is behaving in ways doctors have never seen before. According to new research, vaccinated sperm is refusing to swim and instead ties itself into knots by self-assembles into bizarre 3D ribbon-like structures. But it gets even worse for vaccinated men, as doctors are now warning the unvaccinated to avoid sleeping with them under any circumstances.

TPV Sean

555,007 次观看 • 1 年前

Today we’re announcing @kodezi Chronos-1. After years of research, iteration, and failure, we’ve built something radically new. Chronos-1 is the world's first large language model purpose-built for debugging. Unlike LLMs that just autocomplete, Chronos-1 understands, diagnoses, and heals code.While most LLMs are trained to generate code, Chronos-1 is trained to investigate, remember, and resolve it. What makes Chronos-1 different: - Debugging-first architecture - Multi-level memory engine trained on millions of bugs, logs, and test cases - Adaptive retrieval that scales to entire codebases - 23% better bug detection and 40% fewer debugging cycles in real-world evaluation - Native integrations with IDEs, CI/CD, and observability workflows Chronos-1 powers Kodezi OS, your AI-native CTO that autonomously maintains, evolves, and governs your codebase. Kodezi OS exits beta in Q1 of 2026. We’ve raised a fresh round of funding and are focused on becoming the leader in code maintenance. We’re hiring cracked engineering and product talent, with base starting at $200K. If you’re interested in building the future of code maintenance and helping shape how software heals and improves itself, message me.

Today we’re announcing @kodezi Chronos-1. After years of research, iteration, and failure, we’ve built something radically new. Chronos-1 is the world's first large language model purpose-built for debugging. Unlike LLMs that just autocomplete, Chronos-1 understands, diagnoses, and heals code.While most LLMs are trained to generate code, Chronos-1 is trained to investigate, remember, and resolve it. What makes Chronos-1 different: - Debugging-first architecture - Multi-level memory engine trained on millions of bugs, logs, and test cases - Adaptive retrieval that scales to entire codebases - 23% better bug detection and 40% fewer debugging cycles in real-world evaluation - Native integrations with IDEs, CI/CD, and observability workflows Chronos-1 powers Kodezi OS, your AI-native CTO that autonomously maintains, evolves, and governs your codebase. Kodezi OS exits beta in Q1 of 2026. We’ve raised a fresh round of funding and are focused on becoming the leader in code maintenance. We’re hiring cracked engineering and product talent, with base starting at $200K. If you’re interested in building the future of code maintenance and helping shape how software heals and improves itself, message me.

Ishraq Khan

125,140 次观看 • 7 个月前

New course: Transformers in Practice. You'll get a practical view of how transformer-based LLMs work, so you can reason about their behavior, diagnose problems like slow inference, and make smarter decisions about deployment. This course is built in partnership with AMD and taught by Sharon Zhou. You'll see how transformers generate text one token at a time, how the model decides which earlier words matter most when predicting the next one, and how techniques like quantization speed up inference on GPUs. This is not a video-only course; interactive visualizations throughout let you play with these concepts and build intuition that sticks. Skills you'll gain: - Understand why LLMs hallucinate, and RAG and chain-of-thought shape what they generate - Look inside the model to see how attention and layers combine to predict the next token - Diagnose inference bottlenecks and learn the techniques that speed up transformers on GPUs Join and understand what's really happening inside your LLMs:

New course: Transformers in Practice. You'll get a practical view of how transformer-based LLMs work, so you can reason about their behavior, diagnose problems like slow inference, and make smarter decisions about deployment. This course is built in partnership with AMD and taught by Sharon Zhou. You'll see how transformers generate text one token at a time, how the model decides which earlier words matter most when predicting the next one, and how techniques like quantization speed up inference on GPUs. This is not a video-only course; interactive visualizations throughout let you play with these concepts and build intuition that sticks. Skills you'll gain: - Understand why LLMs hallucinate, and RAG and chain-of-thought shape what they generate - Look inside the model to see how attention and layers combine to predict the next token - Diagnose inference bottlenecks and learn the techniques that speed up transformers on GPUs Join and understand what's really happening inside your LLMs:

Andrew Ng

118,378 次观看 • 2 个月前

🚨 BREAKING: A research lab just released a 15B model that generates multilingual talking human videos with synced audio, beats every competitor in human evaluation, and runs in 38 seconds on one GPU. It's called daVinci-MagiHuman. The key insight is that every other model in this category stacks cross-attention, multi-stream pipelines, and separate conditioning branches to handle video and audio together. This one throws all of that out and uses a single unified self-attention stream across all modalities. Super-resolution happens in latent space rather than pixel space so there's no extra VAE decode-encode round trip. The turbo VAE decoder cuts decoding overhead even further. The distilled version runs in 8 steps with no CFG at all. Visual quality, text alignment, and word error rate all beat Ovi 1.1 and LTX 2.3 on the benchmark table. 100% Opensource. Apache 2.0. Repo and research paper links are in the comments.

🚨 BREAKING: A research lab just released a 15B model that generates multilingual talking human videos with synced audio, beats every competitor in human evaluation, and runs in 38 seconds on one GPU. It's called daVinci-MagiHuman. The key insight is that every other model in this category stacks cross-attention, multi-stream pipelines, and separate conditioning branches to handle video and audio together. This one throws all of that out and uses a single unified self-attention stream across all modalities. Super-resolution happens in latent space rather than pixel space so there's no extra VAE decode-encode round trip. The turbo VAE decoder cuts decoding overhead even further. The distilled version runs in 8 steps with no CFG at all. Visual quality, text alignment, and word error rate all beat Ovi 1.1 and LTX 2.3 on the benchmark table. 100% Opensource. Apache 2.0. Repo and research paper links are in the comments.

Ihtesham Ali

45,152 次观看 • 3 个月前

From Palantir and Two Sigma to turning mechanistic interpretability into a production-grade platform, Mark Bissell (Member of Technical Staff) and Myra Deng (Head of Product) are building Goodfire on the belief that “understanding what’s inside the model” is the path to safer, more controllable AI and Goodfire just raised a $150M Series B at a $1.25B valuation to scale that bet. We sat down with Mark and Myra to unpack what actionable interpretability looks like beyond demos: why SAE features can lose to raw-activation probes on real detection tasks, how they deployed token-level PII monitoring with Rakuten across English + Japanese without training on real customer data, and what it takes to do real-time steering on a trillion-parameter model (including the infamous Gen-Z feature). We also dig into hallucination detection, surgical post-training edits for bias/unlearning, the emerging equivalence between activation steering and in-context learning, and their push to bring interpretability into training so model development isn’t just “data in, weights out.” Goodfire mark bissell Myra Deng

From Palantir and Two Sigma to turning mechanistic interpretability into a production-grade platform, Mark Bissell (Member of Technical Staff) and Myra Deng (Head of Product) are building Goodfire on the belief that “understanding what’s inside the model” is the path to safer, more controllable AI and Goodfire just raised a $150M Series B at a $1.25B valuation to scale that bet. We sat down with Mark and Myra to unpack what actionable interpretability looks like beyond demos: why SAE features can lose to raw-activation probes on real detection tasks, how they deployed token-level PII monitoring with Rakuten across English + Japanese without training on real customer data, and what it takes to do real-time steering on a trillion-parameter model (including the infamous Gen-Z feature). We also dig into hallucination detection, surgical post-training edits for bias/unlearning, the emerging equivalence between activation steering and in-context learning, and their push to bring interpretability into training so model development isn’t just “data in, weights out.” Goodfire mark bissell Myra Deng

Latent.Space

19,389 次观看 • 5 个月前

Interviews from today to come tomorrow, but on a final note today, this video has stuck in my mind since the game finished. Emotion everywhere, in different ways, for so many reasons. End of an era, new journeys beginning, some across seas, several hopefully staying in the Welsh game. Wrexham U19s winning a trophy they've been so close to winning on three occasions, and winning it in their final season as a group, feels fitting with the season and journey the women's and girls section has been on this season. Sad that it's the end of U19s football in North Wales, but the talent on display today and throughout the season gives a lot of hope that if the opportunities are presented, a lot of very good footballers will be coming through the ranks.

Interviews from today to come tomorrow, but on a final note today, this video has stuck in my mind since the game finished. Emotion everywhere, in different ways, for so many reasons. End of an era, new journeys beginning, some across seas, several hopefully staying in the Welsh game. Wrexham U19s winning a trophy they've been so close to winning on three occasions, and winning it in their final season as a group, feels fitting with the season and journey the women's and girls section has been on this season. Sad that it's the end of U19s football in North Wales, but the talent on display today and throughout the season gives a lot of hope that if the opportunities are presented, a lot of very good footballers will be coming through the ranks.

Harry Ware

14,162 次观看 • 2 个月前