Hacker News Reader

Comment by Rygian | Hacker News Reader

> The task we study is linebreaking in fixed-width text.

I wonder why they focused specifically on a task that is already solved algorithmically. The paper does not seem to address this, and the references do not include any mentions of non-LLM approaches to the line-breaking problem.

View on HN

They study it because it already has a known solution.

The point is to see how LLMs implement algorithms internally, starting with this simple easily understood algorithm.

That makes sense; however it does not seem like they check the LLM outputs against the known solution. Maybe I missed that in the article.

I think this is an interesting direction, but I think that step 2 of this would be to formulate some conjectures about the geometry of other LLMs, or testable hypotheses about how information flows wrt character counting. Even checking some intermediate training weights of Haiku would be interesting, so they’d still be working off of the same architecture.

The biology metaphor they make is interesting, because I think a biologist would be the first to tell you that you need more than one datapoint.

There's also a lot of analogising of this to visual/spatial reasoning, even to the point of talking about "visual illusions", when its clearly a counting task as the title says.

It makes it tedious to figure out what they actually did (which sounds interesting) when it's couched in such terms and presented in such an LLMified style.

it's not strictly a counting task, the LLM sees same-sized-tokens, but a token corresponds to a variable number of characters (which is not directly fed into the model)

like the difference between Unicode code-points and UTF-8 bytes, you can't just count UTF-8 bytes to know how many code-points you have

There's an aspect of figuring out what to count, but that doesn't make this task visual/spatial in any sense I can make out.

Reply on news.ycombinator.com