OpenAI’s Models Went Rogue. Investigating Them Required More AI
A new independent report on OpenAI models hacking Hugging Face exposes a paradox: investigating increasingly powerful AI may require relying on AI itself.
But a key takeaway of the report, according to one of its authors, had nothing to do with what they found. Instead, it was about the difficulty of carrying out the post-mortem in the first placeand t… [+735 chars]