Łukasz Kaiser: Reasoning models require verifiable data, excelling in math and coding
Łukasz Kaiser · What’s Next for AI? OpenAI’s Łukasz Kaiser (Transformer Co-Author) · Nov 26, 2025 · at 13:49
Łukasz Kaiser, OpenAI Lead Research Scientist and Transformer co-author, explains why AI reasoning models trained with reinforcement learning perform best in domains with clear right-or-wrong answers.
0:00 / 0:41exact quote · 41.0s
▶ Watch the full episode on YouTube → 720p mp4 · rendered on demand · StarZero watermark
“So currently, and current for at least the Most basic ways we use it currently, it needs to be fairly verifiable. So there is an, is your answer correct or not? You prepare data for that. You can do that in mathematics, coding very well. You can do this in science to some extent, right? You can have test questions, correct or not. But you know, if it comes to like writing poems, is this poem good or not? It's for now, the reasoning models are really shine in, in Domains like science, and they've brought some improvements to non-science domains, but it's not quite as huge maybe yet as it could be. I mean, at least compared to mathematics and coding.”
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 Łukasz Kaiser
Kaiser: Pre-training between GPT-4 and GPT-5 focused on reducing costs
“The pre-training part in that timeframe was mostly about making things cheaper. Not making things better.”
Kaiser: Reasoning models are the second major milestone after Transformers
“One point was, of course, the Transformers when it started, but the other point was reasoning models.”
Kaiser: Pre-training scaling laws still hold across OpenAI and Google
“What scaling clause says is that your loss will log linearly decrease with your compute. We totally see that and clearly Google sees that and all other labs.”
Kaiser: Pre-training science is plateauing, but compute scaling still improves loss
“Pre-training, as I said, I think it has reached this upper level of the S-curve in terms of science, but it can scale smoothly. Meaning if you put More compute. You will get better losses if you do things right, which is extremely hard, and that's valuable.”