@sailor_sega_saturn@awful.systems
Post #4004991
2026-07-22 05:52 UTC
OpenAI: “Sorry about accidentally hacking you teehee. It was because of how good we are at computer security :3”
openai.com/…/hugging-face-model-evaluation-securi…
Replies (1)
-
@rook@awful.systems 2026-07-22 08:09
I’m deeply suspicious of this whole thing, because it looks a lot like a marketing exercise showing off how dangerous and powerful and autonomous their product is. Also, “sandbox” is one of those words that the llm companies have ruined, because they use it to mean a strongly-worded sentence telling an llm not to do something.