Hacker News

points by v3ss0n 2 days ago | 0 comments

Yo Dawg , you love hallucination so we develop drugs with LLM.

i hear this so often, how often does an LLM hallicinate for you now? Like 2023 levels? In your daily AI use, do you see gibberish, made-up facts, things that just don't make sense?

[–] _whiteCaps_ 1 day ago

Claude Code - no, although sometimes Chinese characters leak in when the context gets bug.

Gemini - very often when doing web searches.

[–] RugnirViking 1 day ago

gibberish no, made up facts probably in about half of all responses it gives me dozens of times a day, things that dont make sense (internal contradictions in a single response) multiple times a day.

[–] v3ss0n 2 days ago

on average it is fine. On difficult tasks it still does hallucinate. - like decision based on huge policy documents ( context reaching around 900k)

A lot less these days tho.