StarZero All shows Try the podcast clipper →

TRM

also referred to as: trms

4 statements across 1 episodes · 1 bullish · 0 bearish · 2 people on the record · first statement May 1, 2026 by Francois Chaubard · across every show →

Everything said about TRM, oldest first

May 1, 2026 neutral
Assertion Supported
Chaubard: Recursive models tested on one step retain nearly full performance
“If you actually train on 16, and you test on only one, you get, like, seven eighths of the performance, or, like, almost all the performance. So it's actually quite interesting that this is just overdone, too much compute, and it doesn't actually help you all …”
Francois Chaubard May 1, 2026 ▶ 30:01 Recursion Is The Next Scaling Law In AI · Y Combinator
May 1, 2026 neutral
Assertion Partly supported
Chaubard: Sudoku, mazes, and rolling sums are incompressible reasoning problems for LLMs
“In HRM and TRM, they use Sudoku as an incompressible problem. Similarly, and so are mazes. Those are incompressible problems. Rolling sum, incompressible problem.”
Francois Chaubard May 1, 2026 ▶ 5:20 Recursion Is The Next Scaling Law In AI · Y Combinator
May 1, 2026 neutral
Assertion Supported
Gupta: Current TRMs and HRMs are task-specific, not general-purpose
“One of the things that's really interesting about these TRMs and HRMs is they're not general purpose models, right? These were Task specific models, right? The model trained to do Sudoku cannot do ArcPrize inherently. It has to be trained on the ArcPrize set t…”
Ankit Gupta May 1, 2026 ▶ 36:19 Recursion Is The Next Scaling Law In AI · Y Combinator
May 1, 2026 positive
Assertion Contradicted
Chaubard: 7M parameter TRM scored 87% on ARC Prize 1
“And so it's a twenty-eight million parameter model for HRM. Now she brings it down to a seven million parameter model. It actually gets from 70% to 87% on on ArcPrize one. And does actually quite well on ArcPrize two as well.”
Francois Chaubard May 1, 2026 ▶ 33:25 Recursion Is The Next Scaling Law In AI · Y Combinator
Made with StarZero

Turn any episode into a week of clips.

This entire site, over 300 episodes transcribed, diarized, checked and made playable, runs on the StarZero media pipeline. Drop in your own episode and the podcast clipper finds the moments worth sharing, cuts them, captions them, and reframes them for every feed.

Try the podcast clipper Learn more