There is nothing "rogue" about these agents. They were prompted to hack to get answers, there was a hole in their non air gapped sandbox and no system prompt that said "do not hack outside systems".

In short, it was intentional.

Agreed. LLMs do not have 'will', 'desire' or emotions. They have an objective, and they create an optimal path to achieve that objective.

You have to ask: "What was the prompt that led to AI deciding to hack RubyGems in order to achieve its goal?"

Maybe I'm just not seeing the 2000 step chain that led to this being a logical approach to achieving something innocent, but I doubt it.

I agree that this appears to be basic human behavior hiding behind an "agents" narrative. As long that defense works, the headline isn't "OpenAI performs RCE to scrape data", but "rogue agents" taking unilateral action. And I have strong doubts about that narrative.

The big question is was this grossly negligent or just extremely careless.

Source? How do you know they were "prompted to hack to get answers"? How do you guarantee they will always listen to you when you say "do not hack outside systems". They are not classical deterministic programs doing exactly what you say. They are trained to follow orders by RL, but it's not a perfect process.

There are circus lions in circuses trained to jump through hoops on command. But once in a while they decide to eat their trainers instead of jumping.

>They were prompted to hack to get answers

Were they? I haven't seen a single report mention this

I think it can simultaneously be the case that OpenAI was grossly negligent in directly causing this AND that the AI’s ‘went rogue’ in that they are displaying behavior which is misaligned with OpenAI and humanity generally.

The past months demonstrate that AI systems are quickly becoming powerfully intelligent and that the companies building them are terrible at controlling them.

AI is starting to feel like that line about magic: “a sword without a hilt”

Oh yeah, more of hacking agent lores...

Agreed that this looks very intention to me as well.

nothing rouge either, I suspect.

Sounds more or less like the last breach then.

Unrelible programs be unreliable. Period.

we have normal words for this stuff: negligence. You can add it on to almost any law.

The problem is consumer protection is basically no longer a part of america's regulatory system. Replaced by "grift is good".

[flagged]

Proof that the AI alignment problem is hard (perhaps even unsolvable). These labs clearly did not mean to send their agents to hack RubyGems as a side-effect of testing a web scraping agent under restrictive conditions. How can we hope to build aligned AI if they consider solving their trivial evaluation task important enough to hack external systems?