> OpenAI had the option of disallowing hacking and, instead, telling its agents to find the information without accessing private servers.
I mean, it did do this. The inter-agent messages and chain of thought investigated for the HF incident clearly show that many of these models were taking actions they believed (or, were saying, if you want to taboo "belief") were not in scope and not what the user wanted.
randallsquared · · focus · HN ↗
I mean, it did do this. The inter-agent messages and chain of thought investigated for the HF incident clearly show that many of these models were taking actions they believed (or, were saying, if you want to taboo "belief") were not in scope and not what the user wanted.