Press Space to continue
Agent oversight through message-sending mechanisms
Press Space to continue
What would have happened if there was a tool call for agents to send messages to human overseers, and a reward for doing so in appropriate circumstances? https://x.com/nbaschez/status/2094047815…
Zvi Mowshowitz@thezviAug 29
METR and Redwood Offer Holy #%^@ Postmortem Of The HuggingFace Hack Yesterday I covered the OpenAI technical report on the HuggingFace hack. That report had one key new piece of information, and some good prosaic steps OpenAI will be taking to strengthen its
