Thinking intensity does boost capability: R1-Zero paper cited amid DeepSeek max-vs-high setting debate
karminski3 · x · 2026-09-14
Blogger karminski3 weighs in on the debate over whether DeepSeek models should run with max or high thinking intensity, rejecting the claim that reasoning effort doesn't affect performance. He cites the DeepSeek-R1-Zero paper: with pure RL and no new knowledge added, simply letting chains of thought grow longer lifted AIME24 scores from 15% to 71% — evidence that stronger thinking intensity means stronger capability.
He links three discussions: why max settings can invert SWE-bench results, whether max is actually optimal, and how to make models stop thinking at the right time. The linked Fudan NLP paper, Reward Hacking in the Era of Large Models, surveys how optimizing against imperfect proxy signals in RLHF/RLVR breeds reward hacking and emergent misalignment.
His thesis: a true SOTA model should be a perfect information compressor — solving the hardest problems with the fewest tokens, not dumping lengthy reasoning before an answer.
Related event: Debate Erupts Over Whether DeepSeek Thinking Intensity Affects Performance(4 posts)→
More from Models
- Anthropic removes 5-hour usage cap for verified Claude Ultra subscribers — james_mtc · 2026-10-31
- DeepSeek's silent downtime upgrade caught by the pelican bicycle test — teortaxesTex · 2026-10-31
- ARC Prize 2026 closes in 3 days as Yi-Chia Chen tops ARC-AGI-3 at 75.56% — GregKamradt · 2026-10-31
- Fable 5.5 Max stuns with gorgeous SVG of a pelican riding a bicycle, headed to Claude Code — ChrisGPT · 2026-10-31
- OpenAI reportedly to train on users' Daybreak sessions with no opt-out — dyn___ · 2026-10-31
- NVIDIA Nemotron 3.5 scales LLM self-verification, +9-10 points on agentic benchmarks — sarahcat21 · 2026-10-31