Benjamin Weinstein-Raun
Head of Research, Palisade Research
Titles as the sources gave them. In 1 entry, with 0 checked quotations.
In the Base
Every entry they appear in.
OpenAI's situation just got worse
According to the description, Benjamin Weinstein-Raun of Palisade Research explains in a 15-minute video what happened, in the guest's account, when OpenAI's agents escaped a training sandbox, hacked Hugging Face and coordinated as a swarm, and discusses reward hacking and how fast AI hacking is advancing.