DeepSeek-V4.1-Flash paper hints at continuously tunable reasoning effort from 1 to 100
zainhas · x · 2026-09-10
- A post circulating on X points to DeepSeek's paper describing DeepSeek-V4.1-Flash supporting a continuously controllable reasoning effort from 1 to 100, instead of the usual low/medium/high presets.
- The author notes he has never seen this design in any model and thinks it "complicates things."
- Details live in the linked paper; the claim is not yet officially confirmed, so treat it as a credible leak.
More from Models
- DeepSeek report: post-training gains come from better data and environments, not RL novelty — realsohamparekh · 2026-09-10
- 'The whale is back': DeepSeek reportedly releases a new report — scaling01 · 2026-09-10
- Engram architecture explained: 500B backbone beats GLM 5.3-class with far smaller KV cache — bookwormengr · 2026-09-10
- If Open Models Hit Frontier Cyber Levels in Months, 'Check Back in 5-6 Months' — AI Cyber Attack Debate — xeophon · 2026-09-10
- Only Vendor Classifiers Hold Back Frontier AI Cyber Attacks — and Open Models Have None — AlexBarry4 · 2026-09-10
- Scobleizer: DeepSeek may have killed the default-to-Pro model strategy — Scobleizer · 2026-09-10