Comment

Comment on Gemini AI tells the user to die — the answer appeared out of nowhere when the user asked Google's Gemini for help with his homework

meyotch@slrpnk.net ⁨3⁩ ⁨days⁩ ago

I suspect it may be due to a similar habit I have when chatting with a corporate AI. I will intentionally salt my inputs with random profanity or non sequitur info, for lulz partly, but also to poison those pieces of shits training data.

source

Sort:hotnew top

catloaf@lemm.ee ⁨3⁩ ⁨days⁩ ago
I don’t think they add user input to their training data like that.

source
- kitnaht@lemmy.world ⁨3⁩ ⁨days⁩ ago
  They don’t. The models are trained on sanitized data, and don’t permanently “learn”. They have a large context window to pull from (reaching 200k ‘tokens’ in some instances) but lots of people misunderstand how this stuff works on a fundamental level.
  
  source
  - kboy101222@sh.itjust.works ⁨3⁩ ⁨days⁩ ago
    True, but I’m still gonna swear at it until I get to talk to a human
    
    source