artichoke99

joined 2 months ago

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 in c/[email protected]

[–] [email protected] 15 points 1 month ago

OK but the llm is evidently shit at math so its "non-standard" approach should still be adjusted

*Permanently Deleted* in c/[email protected]

[–] [email protected] 23 points 2 months ago (1 children)

oh good, they're advocating for the physical and psychological torture of children again