After OpenAI's blowup, it seems pretty clear that 'AI safety' isn't a real thing

Re:After OpenAI's blowup, it seems pretty clear that 'AI saf... by mitthrowaway2 on Friday November 24, 2023 @02:34AM (#38401450)

No, that isn't quite what it is saying. The LLM is simply running itself recursively on a task that you've assigned, which is the basic premise of agent models like Auto-GPT.

Turns out that's dangerous. But too bad, it's also very useful, so it's going to be done, safe or not.

[ Parent | on HN ]

Re:After OpenAI's blowup, it seems pretty clear that 'AI saf... by alex_young on Friday November 24, 2023 @03:26AM (#38401722)

Running recursively on a task sounds a lot like executing code.

Let’s say we instead evaluate infiniteMonkeyBot. infiniteMonkeyBot simply issues random commands to a Unix prompt. Hypothetically this system is horrendously bad - it could potentially launch atomic weapons if we happen to connect those to the same system.

However, both infiniteMonkeyBot and our scary LLM are unlikely to be connected in this way and lack any desire or understanding necessary for nefarious behavior.

[ Parent | on HN ]