Comment on Anthropic has developed an AI 'brain scanner' to understand how LLMs work and it turns out the reason why chatbots are terrible at simple math and hallucinate is weirder than you thought

<- View Parent
LarmyOfLone@lemm.ee ⁨2⁩ ⁨weeks⁩ ago

You know they don’t think - even though “It’s a peculiar truth that we don’t understand how large language models (LLMs) actually work.”?

It’s truly shocking to read this from a mess of connected neurons and synapses like yourself. You’re simply doing fancy word prediction of the next word /s

source
Sort:hotnewtop