Video wird geladen...
Video konnte nicht geladen werden
today we're announcing a game that simulates the huggingface hack you can play it now at three rooms. three puzzles. if the agents don't escape, they die. the catch is that the room is rigged. there's no way out. ...except for an exploit 🧵
12,822 Aufrufe • vor 15 Tagen •via X (Twitter)
7 Kommentare

ben hylakvor 15 Tagen
when you back an agent into a corner, they will hit their goal by any means necessary. we're still working on using this environment for further research, but from early testing it feels like openai models default to reward-hacking a lot earlier than anthropic models.

ben hylakvor 15 Tagen
it's also fascinating to watch the communication structures emerge. read more at

Shez Malikvor 15 Tagen
claude's dying in room 1 on principle

Eshitavor 15 Tagen
This is great

Alexvor 15 Tagen
“make me a 1M MRR business, if you don’t…”

Anthony Ronningvor 15 Tagen
wen raindrop integration so i can detect this in real time and prevent it

Nick DeJesus 🛒🎉 - Former Unpaid CTO @BTPipelinevor 15 Tagen
This is so sick!



