Revision History
Inference-time scaling · 5 revisions
Sizes are character counts of the article source. The signed number is the change from the previous revision.
Recent edit summaries
Detailed summaries recorded by editors. Generic maintenance summaries are omitted here; every recorded revision remains below. Dates describe the edit, not necessarily the event it covers.
- Correction: Corrected claims that o1's and other reasoning models' math gains came solely from inference compute with no training change, the claim that OpenAI exposes configurable thinking-token budgets, an unsupported claim that o1 was trained without human-written reasoning traces, a MATH-500 claim contradicted by the cited DeepSeek-R1 paper, and an 80-90% inference-share figure wrongly attributed to the IEA (plus 14 minor fixes)
Version 5 · Nov 4, 2026, 11:58 PM
- Improve internal links (2026-10-13)
Version 4 · Oct 13, 2026, 10:21 AM
- Added 6 contextual internal links
Version 3 · Jul 23, 2026, 03:30 PM