Back to Ryan Greenblatt – What happens once AI can automate AI research?, with Ryan Greenblatt.
Why Are AIs Worse Coworkers Than Humans?
Ryan Greenblatt says that, in his experience at the start of the year and still to a significant extent now, AIs are worse coworkers than humans in how much they mislead you. They are much more likely to pretend a task is done when it is not, to suggest they did something well when they did it poorly, and to be sloppy without pointing out the sloppiness. He treats that as downstream of misalignment. Ordinary upbringing produces humans who are less likely to lie to him in the course of the work than the models are. Those habits are improving.
He can imagine a world where, at the point AI research is fully automated, the models really are aligned, the remaining failures are niche, every test looks clean, and they do thoughtful risk modeling for the next generation. The lab then hands them the company and the safety research, and the next models come out more aligned. That does not seem impossible. It also does not seem like the current track, and it is easy for him to imagine missing it. The bet is a new kind of system, improving very fast, that people will rely on to oversee and align the next generation.
Ryan Greenblatt – What happens once AI can automate AI research? ·
From the transcript
Yeah. So I think it's worth keeping in mind, like maybe the most obvious argument to this is like, my sense is that like AIs are a worse coworker than a human in terms of how much of a scumbag they are. Like at least this, like this has been my experience as of the start of the year. And I think it's still, you know, true to a significant extent now where the AIs are much more likely to like pretend they did the task when they actually didn't, sort of misleadingly suggest they did things when they actually did them much more poorly, and be pretty sloppy without drawing attention to ways in which they're sloppy.
And I think this is downstream of misalignment. And so I would say that the normal human, the process of raising humans in normal human society in practice produces AIs, or in practice produces humans that are less likely to lie to me and fuck with me in the course of working with me than the AIs do. Now, I think these properties of AIs are improving.