Revision History
Red teaming (artificial intelligence) · 7 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 the start date of Anthropic's NNSA nuclear red-teaming partnership (April 2024, not April 2025), the institution behind PAIR (University of Pennsylvania, not Carnegie Mellon), the publication date of OpenAI's external red teaming paper (November 2024), the current CyberSecEval version (4, released April 2025), and the EU AI Act fine levels and timing that apply to GPAI providers (plus 31 minor fixes)
Version 7 · Nov 2, 2026, 10:31 AM
- Improve internal links (2026-10-13)
Version 6 · Oct 13, 2026, 10:07 AM
- Added 6 contextual internal links
Version 5 · Jul 23, 2026, 03:04 PM