DeepSeq R1

concept
1 mentions 1 recordings first heard Nov 2025 last heard 25 Nov ↑1 vs the 12 months before

Paper describing the DeepSeq R1 reinforcement learning approach

Trend

mentions per week · public audio 7d30d6M12M
1 · 19 Nov SepDecMarJunnow

Peak in the week of 19 Nov — 1 mentions across 1 series.

Moments

newest first · ▶ plays the moment
DwarkeshDwarkesh Podcast · Ilya Sutskever — We're moving from the age of scaling to t... · 15:52 · 25 Nov
…this was in the DeepSeq R1 paper, is that the space of trajectories is so wide that maybe it's hard to learn a mapping from an intermediate trajectory and value.…
· Open transcript →
All 1 moments