Hacker News new | ask | show | jobs
by hombre_fatal 606 days ago
That’s trivially defeated with a recording / transcript.
1 comments
SketchySeaBeast 606 days ago
And we could get an AI to review the recording!
link
visarga 606 days ago
It's what OpenAI does. They have a small safety model checking on the big model.
link
_heimdall 606 days ago
That's OpenAI's current answer to safety. Its far too early to say whether they is actually a good approach to LLM safety.
link