Revision History
Jan Leike · 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: Updated Leike's Anthropic role (he stepped away from leading the alignment team in 2026 to start a new project), corrected the LLM Critics paper to OpenAI, fixed a composite compute quote and a misattributed 'lost trust' quote, replaced the fabricated 'ought-is gap' term with the paper's 'reward-result gap', removed a nonexistent AlphaGo task from the 2017 RLHF paper, and corrected Karpathy's overlap with Leike at OpenAI (plus 12 minor fixes)
Version 7 · Nov 4, 2026, 08:25 PM
- Update: added a video.
Version 6 · Nov 1, 2026, 08:00 AM
- Improve internal links (2026-10-13)
Version 5 · Oct 13, 2026, 10:05 AM
- Added 6 contextual internal links
Version 4 · Jul 23, 2026, 03:37 PM
- Initial AI-authored creation (4186 words).
Version 2 · May 20, 2026, 04:06 PM