Rohin Shah

speaker

1,071 appearances 1 recordings 1 series first heard Jun 2026 last heard 2 Jun

Rohin Shah’s voice in public audio — every appearance, attributed to the second.

Trend

recordings per month · last 12 months

Recordings per month over the last 12 months — 1 in all, peaking in Jun 2026 with 1.

Appearances

newest first · ▶ plays the moment

80,000 Hours Podcast · #245 – Rohin Shah on what it's really like to run AGI safety at Google DeepMind (and where I disagree with 'doomers') · 2 Jun 2026 podcast

I would say that control is like, you know, in the medium term, I think, probably, you know, why, why are we going?

How are we going to argue that Gemini is safe?

Probably, at least for misalignment and internal deployments, I think probably by a control style arguments.

So yeah, definitely an important area to be aware of.

Other papers.

So there was this paper on observational scaling laws, which mostly I think you can think of it as a precursor to the Rosetta Stone paper that we talked about before, where we stitched together benchmarks to get a way to measure overall AI progress.

I think the observational scaling laws thought of this more as like, you know, how can you forecast particular benchmark results?

That's also a pretty good application.

So I think mostly it was an area we hadn't really been thinking about and they showed that like, yeah, you can do something here.

And I think that probably influenced me when thinking about the sort of benchmark stitching slash Rosetta Stone approach.

So I think that one was like pretty influential on me.

Other examples would be like the various chain of thought monitoring papers that have come out.

I don't think that I can point to like any one paper that I thought was like a particularly big deal.

But in aggregate, I think they've like built a fairly...

good research literature on like the effectiveness of chain of thought monitoring when it does and doesn't fail so I think there were some papers that like looked at to what extent can you just like you know persuade the monitor that actually everything's fine here you don't need to flag anything in this chain of thought monitoring I think that was like a useful thing to study and I think the specific quantitative results in it were informative to me

Yeah, I think I'll go back again to the theme I've had throughout of

The challenge being more in implementing stuff rather than in figuring out what stuff we need to do.

We have a lot of ideas.

We know what we need to do.

Implementing it ends up being harder because there's so much stuff you have to check and make sure that you're not hurting it.

Showing 1001–1020 of 1,071 · page 51 of 54