Comment by foltik
2 months ago
Sounds like they did the ol “grok please make this secure” and it slopped out this plausible-if-you-squint nonsense.
Rendering untrusted model output, ooh scary! Of course we want full audit surface!
2 months ago
Sounds like they did the ol “grok please make this secure” and it slopped out this plausible-if-you-squint nonsense.
Rendering untrusted model output, ooh scary! Of course we want full audit surface!
Yep that’s some classic “task 1000% complete” best-guess-of-user-intent LLM babble.