Hacker News Reader

Then test it. Make several small companies. Create an office space, put people to work there for a few months, then simulate an AI replacement. All testing methodology needs to be written on machines that are isolated or better always offline. Except CEO and few other actors everyone is there for real.

See how many AIs actually follow up on their blackmails.

View on HN

No need. We know today's AIs are simply not capable enough to be too dangerous.

But capabilities of AI systems improve generation to generation. And agentic AI? Systems that are capable of carrying out complex long term tasks? It's something that many AI companies are explicitly trying to build.

Research like this is trying to get ahead of that, and gauge what kind of weird edge case shenanigans agentic AIs might get to before they actually do it for real.

Not a bad idea. For an effective ruse, there ought to be real company formation records, website, job listings, press mentions, and so on.

Stepping back for a second though, doesn’t this all underline the safety researchers’ fears that we don’t really know how to control these systems? Perhaps the brake on the wider deployment of these models as agents will be that they’re just too unwieldy.

Reply on news.ycombinator.com