Evidence receipt / belief
Published · transcript-backedSholto Douglas: belief
22 May 2025 Dwarkesh Podcast Is RL + LLMs enough for AGI? — Sholto Douglas & Trenton Bricken
“As you use more compute, and as you train on more, and more difficult tasks, your rate of improvement of biology for example is going to be somewhat bound by the time it takes a cell to grow in a way that your rate of improvement on math isn't, for example. So, yes, but I think for many things we'll be able to parallelize widely enough, and get enough iteration loops.”
Source trail
Everything needed to verify it.
- Speaker
- Sholto Douglas
- Attribution
- Verified speaker
- Claim type
- belief
- Recorded
- 22 May 2025
- Publisher
- Dwarkesh Podcast
Transcript context
…I do think there's this notion that the longer, the harder tasks, the more training is required. I'm sympathetic to that naively, but we as humans are very good at practicing the hard parts of tasks, and decomposing them. I think once models get good enough at the basic stuff, they can just rehearse, or fast-forward to the more difficult parts. I mean that's definitely one of the big complexities. As you use more compute, and as you train on more, and more difficult tasks, your rate of improvement of biology for example is going to be somewhat bound by the time it takes a cell to grow in a way that your rate of improvement on math isn't, for example. So, yes, but I think for many things we'll be able to parallelize widely enough, and get enough iteration loops. Will the regime of training new models go away? Will we eventually get to the point where you've got the model, and then you just keep adding more skills to it, with RL training?…
Stored transcript either side of the excerpt. The highlighted words are the published quote; the surrounding text is unedited source, never generated.