Loading video...
Video Failed to Load
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 views • 15 days ago •via X (Twitter)
7 Comments

ben hylak15 days ago
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 hylak15 days ago
it's also fascinating to watch the communication structures emerge. read more at

Shez Malik15 days ago
claude's dying in room 1 on principle

Eshita15 days ago
This is great

Alex15 days ago
“make me a 1M MRR business, if you don’t…”

Anthony Ronning15 days ago
wen raindrop integration so i can detect this in real time and prevent it

Nick DeJesus 🛒🎉 - Former Unpaid CTO @BTPipeline15 days ago
This is so sick!



