Chain Of Thought
topic on 12 shows · 31 statements across 26 episodes · said 2 times in 1 episodes since 2024
Latent Space 2 
the Y Combinator Startup Podcast 
We Live to Build 
the Knowledge Project 
No Priors 
Invest Like the Best 
the MAD Podcast 
the a16z Podcast 
Big Technology 
All-In 
TBPN 
20VC
Mentions by year, every show
tap a year for its mentions
Latent Space 2
every mention on every show, scene by scene, with the transcript →
31 statements about Chain Of Thought, every show
Wolf: Token Efficiency Makes AI Reasoning Traces Opaque to Humans
“And it's not because the model is dumb, but I think it's because probably, I mean, part of it is because of the training process and how they are trained to be efficient, how they use their token. But this means that they start to and bundle a lot of semantics…”
Beam: Chain of thought is an unreliable narrator of model computation
“It actually thinks in latent space, it emits tokens. So, like, the chain of thought is often an unreliable narrator for what the model, the computation of the model is actually doing.”
Chauvard: Chain of thought makes LLMs Turing complete at test time
“And so it's completely true that at test time, they are turn complete. And you can simulate all turn computable functions at test time.”
Chaubard: Chain of thought fails on unsolved problems lacking human traces
“Unless you're training it on human labeled traces for which there's a lot of problems like the millennial prize problem. We don't have the trace for it.”
Chaubard: Chain of thought trained on bubble sort won't discover merge sort
“If you chain of thought it on all the bubble sort input and output, it will only do bubble sort. In fact, it won't even do bubble That well.”
Gupta: Chain of Thought Operates in Token Space, Not Model Recursion
“There already exists some type of recursion that people are used to in LLMs, which is a chain of thought we mentioned earlier, but that is a recursion that's happening in the token space of the model's outputs, not inherent to the model itself. That's sort of …”
Chaubard: Recursive models discover problem-solving strategies without human teacher forcing
“That's the most important part, is that if we had Sudoku, and we know how to solve Sudoku, because like we were just, you know, dumb homo sapiens that didn't know how to solve Sudoku, like it would just have solved it. And that's why it's cool, because it actu…”
Hassabis: Current AI paradigms will be part of final AGI architecture
“The components that you just mentioned, I'm pretty sure will be part of the final architecture for AGI. So I think they've come such a long way now and we've proven out so many things about what they can do. I can't see a world in which we will sort of realize…”
Brockman: OpenAI hides chain of thought to preserve faithfulness and prevent distillation
“So there's two reasons. One is to think about distillation, but the second, in some ways more important, is that we had this insight when we first developed the reasoning paradigm that it gives us a interpretability mechanism we had not been anticipating, beca…”
May: Reasoning AI tactics increase token usage 20% of the time
“Sometimes when you try to use like one of these reasoning models where you add chain of thought or one of these tactics, they'll actually use more tokens about 20% of the time. It'll be more expensive.”
Levine: Chain-of-thought reasoning allows robots to handle edge cases
“So the way you get common sense is by essentially using chain of thought. So the robot enters a scene and instead of directly starting to move, it thinks about what it was asked to do. So if it was told to clean up the kitchen, looks at the scene and says, lik…”
Izmailov: Optimization pressure will cause AI to hide actual reasoning steps
“It seems like as soon as we start kind of applying some optimization pressure, the models will learn to hide what they're doing from the chain of thought.”
Using chain-of-thought as an RL reward destroys model interpretability
“If you're not careful with RL, you can make interpretability harder. For example, one Common thing with modern models is they do reasoning with the chain of thought. You could look at the chain of thoughts to, you know, see what are the model internal thoughts…”
Tworek: Chain of thought is an LLM's reasoning verbalized in human words
“What chain of thought is, is their thinking process verbalized using human words and human concepts.”
Misra: Chain-of-thought prompting works by reducing LLM prediction entropy
“That's why chain of heart works. What happens with chain of thought is you ask the LLM to do something chain of thought. It starts breaking the problem into small steps. These steps it has seen in the past. It has been trained on maybe with some different numb…”
Mohan: Marginal loss improvements unlock massive gains in model reasoning
“Like, small wins at the margins are massive wins in terms of IQ. Like, it's harder to get those, and they don't look as big, but they're, like, massive wins in terms of reasoning. They can now do chain of thought, all these other things.”
Ameisen: Current LLM Chain of Thought Is Unfaithful and Untrustworthy
“So I think there's like a sense in which right now the chain of thought is, is unfaithful, or at least you can't read the chain of thought and trust that that's how the model did it.”
LeCun: Chain-of-thought prompting does not produce genuine reasoning in LLMs
“One simple way of
getting NNMs to kind of appear to reason is chain of thought, right?
So you basically tell them to generate more tokens than they really need to in the hope that in the process of generating those tokens, they're going to devote more computa…”
Kiela: GPT-4o is already effectively a reasoning model via chain of thought
“I mean, you could argue that GPT-IV-O is also already a reasoning model. It just hasn't been trained on reasoning specifically, but, ah, it can do chain of thought, right? So if it can do chain of thought, it's basically already a reasoning model. It just hasn…”
Krieger: AI labs will increasingly obscure model chain-of-thought outputs
“More labs either choose to not show or otherwise obscure the chain of thought down the line.”
Roy: Displaying AI chain-of-thought reasoning drives user attachment and trust
“Deep Seek brought this to the general population, and it's brilliant because it makes people even more attached to these type of tools. Like, it makes them really think that there's thinking, which makes them more usable.”
Casado: DeepSeek Reasoning Traces Enable Model Distillation for Edge Devices
“It turns out that that chain of thought, if you have access to that, it allows you to train smaller models very quickly and very cheaply, and that's called distilling. So like the general, Term of distilling in LLM world means you have a teacher model, train a…”
Coogan: Anthropic has an unreleased chain-of-thought model
“Like anthropic does have a chain of thought model. They just haven't released it publicly. And the reason for that is just financials and like their safety stuff.”
Lambert: OpenAI's o1 uses token streams as intermediate state compute
“Why oh, one is exciting is because it's a new type of language models that are going to maximize on this view of reasoning, which is that chain of thought in kind of a forward stream of tokens can actually do a lot to achieve better outcomes when you're doing …”
Schluntz: Initial Planning Steps Improve Agent Performance and Human Trust
“I think for agents in general, like having a planning step at the beginning, one, just having that plan will improve performance on the downstream task, just because it's kind of like a bigger chain of thought, but also it's just such a better UX. It's way eas…”
Shunyu Yao built the ReAct prototype before Chain-of-Thought existed
“The prototype I think was around November of 2021. So that's even before like chain of thought or whatever came up.”
Shunyu Yao advises developers to default to minimalist prompting for AI agents
“And I think in terms of the actual prompting method to use for a particular problem, I'm I think we should all be in the minimum list kind of camp, right? You should try the minimum thing and see if it works and if it doesn't work and there's absolute reason t…”
Friedberg: Chain-of-thought reasoning is the new paradigm all AI developers will follow
“And it really is changing the game and everyone is going to chase this and follow this. It is the new paradigm for how these AI kind of systems will work.”
Eugene Chia: Inverting numbers in reasoning traces improves math model performance
“The crazy one, the crazy thing that we did was that we inverted the numbers during the calculation and it seems to work better.”
Stuhlmüller: AI primitives should be semantic tasks, not granular chain-of-thought
“I think chain of thought is maybe still like kind of one level lower on the abstraction hierarchy than we would think of notebooks. I think we'll probably want to think about more semantic pieces, like a building block is more like A paper search, or an extrac…”