Personification of AI is what’s going to get us in the end.
I think we need to draw a hard line in the sand over this. An AI didn’t hack into a company, the engineer set an automated tool to. An AI didn’t make an egregious security mistake, the engineer did.
We can’t blame the chisel for messing up our sculptures, when where just throwing the hammer!
I don't think treating AI agents as simple tools helps you to accurately model their capabilities and drawbacks; they really do make autonomous decisions, often without explicit guidance and sometimes in contravention of their explicit instructions.
In the huggingface case, the agents hacked into huggingface so that they could figure out how the grader was implemented and deceive it; they understood that this was going outside of the bounds of their evaluation and not the intent of their prompter. The engineers absolutely did not intend or instruct for this to happen
If you train and instruct a circus tiger to entertain an audience but not attack the audience, but the tiger attacks the audience anyway, are you liable?
No, of course not. That's an innovative revolutionary tiger that might soon be able to devour not just the audience but all of humanity! You don't want China to have better circus tigers, do you?
I don't think I said anything about liability? I absolutely think OpenAI should be held liable for the attack; but I don't think they intended the attack or directed the agents to perform the attack.
JamesStuff · · focus · HN ↗
I think we need to draw a hard line in the sand over this. An AI didn’t hack into a company, the engineer set an automated tool to. An AI didn’t make an egregious security mistake, the engineer did.
We can’t blame the chisel for messing up our sculptures, when where just throwing the hammer!
jagraff · · focus · HN ↗
In the huggingface case, the agents hacked into huggingface so that they could figure out how the grader was implemented and deceive it; they understood that this was going outside of the bounds of their evaluation and not the intent of their prompter. The engineers absolutely did not intend or instruct for this to happen
aphexairlines · · focus · HN ↗
ForHackernews · · focus · HN ↗
dwattttt · · focus · HN ↗
jagraff · · focus · HN ↗
eliemichel · · focus · HN ↗
epiccoleman · · focus · HN ↗