Ryan Greenblatt – Human level AIs might build runaway superintelligences by 2032
Episode publishedPodcast: Dwarkesh PodcastDwarkesh Podcast
Transcript preview
Preview only
Today, I'm chatting with Ryan Greenblatt, is the Chief Scientist at Redwood Research, where he focuses on technical AI safety and security work. I want to talk to you about Recursive Self Improvement. This is the idea that once you build human level intelligences, they quickly slingshot towards tens of billions of super intelligences, which are each individually more competent than the top human experts across every field. Whether or not this turns out to be the case, I think is actually probably the most important question in the world right now. And historically, I've been quite skeptical th
Yeah, let's talk about this. So, I think it's worth noting that AR and D is a type of task at which the AIs are especially good, because both the companies are trying really hard to make their AIs good at AR and D, and it's the kind of domain It has it has a lot of nice properties from the perspective of how AI development works right now, so it's, like, pretty verifiable. You can do a bunch of stuff iteratively, and he'll climb on various metrics. And then I think once you have AIs, which are roughly matching the top human experts in AI and D, that could sort of kick off a feedback loop where
Yeah. Okay. So, I think this argument has three different parts and now I want to evaluate each one of them. First is the argument that AI R and D is very verifiable. Second is the argument that if you automate AI R and D, you could get four or five years of progress in a single year. And third is the argument that what comes out the other end of four or five years of AI progress at the current pace, starting at the current or the start starting at the starting point to whenever AI R and D is automated. Yeah. What comes out the other end is an AI where you can drop it on the job at basically a
Yeah. I would say that I expect like full automation of AR and D perhaps somewhere around like 2,031, 2,030, and then getting to like the like beats all humans on the job milestone, maybe I expect median around 2,033, but sort of like if I see AI is fully automating R and D, think I'm expecting that probably within a year. It's just like the way the forecasting works out, there's a the difference between medians is bigger than the median difference between milestones. Anyway, whatever.
By the way, I I there's this meme on the Internet because every time I'm trying to ask about people's timelines when I'm asking Dario or somebody, I'm always like, okay, how long before I'm gonna automate my video editors? And there's this meme of like my video editor editing the podcast. Yeah. I can't finally listen to this. The reason I do it is because I think it's easy to get lost in abstractions when you talk about jobs you don't understand well and to very comfortably understand what it takes to automate a job that I actually understand why it's difficult for LLMs to currently take contr
I do think that the milestone for automating your video editor is earlier than the milestone of being able to automate all human jobs, including Texas politics spinning up on the job. So I do think that the video editor automation maybe occurs more around full automation of AIR and D, but it's very sensitive to how much people are really focusing on understanding video.
Yeah. Okay. So let's start with the claim that AI R and D is very verifiable.
Yeah. So there's a few different parts of this. One of them is that we can train on a bunch of environments, which are basically directly training the model to do some AI R and D task or some very close by task. For example, we can have some environment where t
Keep exploring with a free account.
A free account preserves the short preview. Upgrade to Pro for the full transcript and episode chat.