Comment on I'm looking for an article showing that LLMs don't know how they work internally
theunknownmuncher@lemmy.world 5 days agoYou’re confusing the confirmation that the LLM cannot explain it’s under-the-hood reasoning as text output, with a confirmation of not being able to reason at all. Anthropic is not claiming that it cannot reason. They actually find that it performs complex logic and behavior like planning ahead.
adespoton@lemmy.ca 5 days ago
No, they really don’t. It’s a large language model. Input cues instruct it as to which weighted path through the matrix to take. Those paths are complex enough that the human mind can’t hold all the branches and weights at the same time. But there’s no planning going on; the model can’t backtrack a few steps, consider different outcomes and run a meta analysis. Other reasoning models can do that, but not language models; language models are complex predictive translators.
theunknownmuncher@lemmy.world 5 days ago
🙃 actually read the research?
glizzyguzzler@lemmy.blahaj.zone 2 days ago
No, they’re right. The “research” is biased by the company that sells the product and wants to hype it. Many layers don’t make think or reason, but they’re glad to put them in quotes that they hope peeps will forget were there.