Revision History
AI control · 8 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.
- Update: fix version-number links (e.g. Claude 3.5 was linked as Claude 3 followed by .5)
Version 8 · Nov 5, 2026, 10:50 AM
- Correction: Corrected the AI Control paper's authors' affiliation (Redwood Research only), the reversed description of Factor(T,U), OpenAI's Preparedness Framework v2 risk categories, the account of DeepMind's Frontier Safety Framework versions, and the stale Anthropic RSP version (plus 21 minor fixes)
Version 7 · Nov 2, 2026, 03:11 PM
- Update: added a video.
Version 6 · Nov 1, 2026, 08:29 AM
- Improve internal links (2026-10-13)
Version 5 · Oct 13, 2026, 10:04 AM
- Added 6 contextual internal links
Version 4 · Jul 23, 2026, 03:33 PM