← All transcripts

The Problem With How LLMs Generate Text - Grant Sanderson Transcript, AI Summary & Key Points

Dwarkesh Patel · Aug 01, 2026 · Science & Technology · 01:06 · EN

Watch on YouTube

AI Summary

Autoregressive generation is described as a strange way to produce writing: repeatedly predicting the next token differs from composing an essay with an overall plan. This process can make intelligence dependent on the immediate context, while the unlikely connections that may contain the most substance are not specifically incentivized because most unlikely continuations are not predictable next tokens. Reinforcement learning may improve performance, but it does not necessarily solve this underlying problem.

Key Points

  • Autoregression repeatedly predicts what will come next rather than composing an essay through deliberate, global planning.
  • Repeated next-token prediction can produce writing that differs substantially from what an intelligent writer would have composed.
  • An autoregressive system may become a slave to its immediate context, drawing in surrounding context when answering a question.
  • The connection containing the most substance may be unlikely by nature, but next-token prediction does not specifically incentivize making such connections.
  • Reinforcement learning can improve a system in some ways, but the transcript questions whether it addresses the incentive problem around unlikely connections.
🔒 Full analysis locked

Unlock more videos and the full analysis

A credit unlocks one video's full analysis for good — the build steps, the tools and how each was used, the methods behind every use case. Pro opens the whole library instead, and raises how many videos you can analyse a day.

Unlock full analysis — free

Transcript

Searchable transcript of The Problem With How LLMs Generate Text - Grant Sanderson — Dwarkesh Patel (01:06). Search for a phrase, then click its timestamp to jump straight to that moment in the video.

Captions sourced from the original video on YouTube, published by Dwarkesh Patel. The video, its captions and all related intellectual property remain the property of their respective owners; AINotes claims no ownership. Provided for research, accessibility and search — see the Transcript Notice and Copyright Policy.

00:00 Auto regression is actually like a really really weird [music] way to produce stuff if you think about it. Like you're an intelligent person. Imagine I locked you in a box and then the only way that you have of interacting with the world is that you receive a slip of paper and then someone says, "Can you like predict what will come next?" And then you predict what will come next and then your memor is [music] wiped.

00:15 Imagine that was done a whole bunch and then what comes out on the other end? They're like, "Look at this essay that [music] you wrote." You might look at that and be like, "This is awful. That's not the essay that I would have written." Right? because like the process of like repeatedly like predicting something is just pretty different from how you would think as a writer to like compose it and think it through and everything [music] and in particular what would probably happen is you're sort of a slave to your

00:32 context where you might be [music] answering some question about some particular field and so you like draw in all the context around that and you're going there the [music] connection that actually is where all the substance is going to come from is like by its nature a very like unlikely one and you can do all the RL that you want to try to like get better in some way but like what's the thing that's specifically incentivizing making these unlikely connections [music] when the vast majority of them aren't the

00:53 predictable, you know, next token that would come in there. And so it's like it might be the case that you just have this intelligence that's sort of locked in there inside that box, but it's just a weird way of interacting with