Yoav Goldberg: I can't explain why SOTA reasoning traces are this good
LabYosi · x · 2026-09-25
NLP researcher Yoav Goldberg says the reasoning traces of current SOTA models on hard coding/logic problems are "just too good" — he has no mental model of how they emerge from RL training, even with initial CoT abilities and billions of rollouts. His best guess: huge spend on human-produced examples plus SFT, but he's not convinced that's the whole story.
Related event: Researchers Debate Where Frontier Models' Reasoning Comes From(12 posts)→
More from Models
- Gemini 4 Carbon matches predecessor's score but explores less, gets distracted — patience_cave · 2026-11-11
- Fable 5.2 takes MazeBench frontier, matches GPT-6 Astra puzzle-solving — patience_cave · 2026-11-11
- MazeBench: Fable 5.2 scores 15%, near-frontier at half price; Gemini 4 Carbon 11% — patience_cave · 2026-11-11
- Indie dev flips from $20 Pro back to $200 Gemini Ultra after two days of deep use — yihui_indie · 2026-11-11
- OpenAI retiring ChatGPT's Standard Voice with 9 original voices on Dec 11, petition launched — ChaosGremlinOG · 2026-11-11
- Leak: Google's upcoming model lineup includes Hydrogen, Krypton, Helix and a video model — koltregaskes · 2026-11-11