Siddharth: Verifiable domains allow self-play reinforcement learning to replace RLHF
Jonathan Siddharth · Inside The $2.2B AI Research Accelerator | Turing · Sourcery with Molly O'Shea · Oct 10, 2025 · at 24:24
Turing CEO Jonathan Siddharth explains the shift in frontier AI model post-training toward automated verifiers and experiential self-play in domains like math and coding.
0:00 / 0:56exact quote · 56.2s
▶ Watch the full episode on YouTube → 720p mp4 · rendered on demand · StarZero watermark
“Now, for these verifiable domains like coding and math, instead of doing reinforcement learning with human feedback, you can do reinforcement learning. Because you can automatically check when you got the correct answer or not in these verifiable domains. And with reinforcement learning, the w the way you teach the model is not through imitation learning, where you're learning from humans, but it's through experiential learning, where you create this environment with prompts and verifiers, and you create basically a mini world model, where as long as the agent gets the right result, ah, that particular trajectory that the agent took to come to the right answer gets reinforced, and when the agent got to a result that didn't get the right answer that doesn't get reinforced. So the model kind of learns from its own experience. It's a form of self-play, which I think is really, really cool.”
quote is from the automated transcript, cleaned for reading: filler sounds and stutters are removed, nothing is rephrased. names can be misheard (the analysis reads context, assessments check outside sources). how →
More from Jonathan Siddharth
Siddharth: Agentic AI will replace services firms like McKinsey, BCG, and Accenture
“So I think like Turing will probably replace companies like McKinsey, Bain, BCG, and every services company like Accenture, TCS, Wipro, Infosys, like all of these companies doing vanilla services that's going to be automated with these agentic systems.”
Siddharth: Solving multimodality, reasoning, tool use, and coding yields ASI
“Turing's the world's leading research accelerator, working with all of these frontier labs to advance them along I would say the four pillars of superintelligence which is multimodality, reasoning, tool use, and coding. If you solve these four things, you will…”
Siddharth: ASI means automating 90% of computer tasks for 90% of humans
“And I think of ASI as us having automated 90% of the tasks that 90% of humans do today in front of a computer, right?”
Siddharth: AI will automate $30 trillion of global knowledge work
“This is like, if you look at those four dimensional, if you look at that four dimensional matrix, that's 30 trillion dollars of knowledge work that is going to be automated.”
Siddharth: Reasoning models ended demand for simple AI data factories
“This industry had a huge shift after the reasoning models came out late last year, O-one being the first. The shift is, before the reasoning models, this industry needed simple data. Gobs and gobs of simple data. You needed a data factory. Or, ah, this industr…”