Y
Hacker News
new
|
ask
|
show
|
jobs
by
foltik
13 days 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
!
1 comments
qlte
12 days ago
Yep that’s some classic “task 1000% complete” best-guess-of-user-intent LLM babble.
link