Comment on OpenAI finds evidence other AI agents escaped containment as it widens hacking probe

Powderhorn@beehaw.org ⁨1⁩ ⁨day⁩ ago

I have a hard time equating “the LLM did what we told it” with “hacking.” But hey, let’s throw “escaped containment” in just to make it Serious™.

source
Sort:hotnewtop