I found the aeticle in a post on the fediverse, and I can’t find it anymore.

The reaserchers asked a simple mathematical question to an LLM ( like 7+4) and then could see how internally it worked by finding similar paths, but nothing like performing mathematical reasoning, even if the final answer was correct.

Then they asked the LLM to explain how it found the result, what was it’s internal reasoning. The answer was detailed step by step mathematical logic, like a human explaining how to perform an addition.

This showed 2 things:

  • LLM don’t “know” how they work

  • the second answer was a rephrasing of original text used for training that explain how math works, so LLM just used that as an explanation

I think it was a very interesting an meaningful analysis

Can anyone help me find this?

EDIT: thanks to @theunknownmuncher @lemmy.world https://www.anthropic.com/research/tracing-thoughts-language-model its this one

EDIT2: I’m aware LLM dont “know” anything and don’t reason, and it’s exactly why I wanted to find the article. Some more details here: https://feddit.it/post/18191686/13815095

  • whaleross@lemmy.worldEnglish
    7·
    3 days ago

    People that can not do Matrix multiplication do not possess the basic concepts of intelligence now? Or is software that can do matrix multiplication intelligent?

    • glizzyguzzler@lemmy.blahaj.zoneEnglish
      1·
      14 hours ago

      So close, LLMs work via matrix multiplication, which is well understood by many meat bags and matrix math can’t think. If a meat bag can’t do matrix math, that’s ok, because the meat bag doesn’t work via matrix multiplication. lol imagine forgetting how to do matrix multiplication and disappearing into a singularity or something

      • whaleross@lemmy.worldEnglish
        1·
        14 hours ago

        Well, on the other hand. Meat bags can’t really do neuron stuff either, despite that is essential for any meat bag operation. Humans are still here though and so are dogs.