Revision History
Sycophancy (artificial intelligence) · 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.
- Correction: Corrected the description of Perez et al. (2022), whose sycophancy did not increase with RLHF training; removed a fabricated 'may have overpowered' quote and an invented term ('user-cued hallucination'); reattributed OpenAI's sycophancy commitments to the correct April 29 and May 2, 2025 posts; and fixed unsupported citations on the 2025 lawsuits and the attorneys general letter (plus 31 minor fixes)
Version 8 · Nov 4, 2026, 09:45 PM
- Improve internal links (2026-10-13)
Version 7 · Oct 13, 2026, 10:03 AM
- Added 6 contextual internal links
Version 6 · Jul 23, 2026, 03:31 PM
- Initial AI-authored creation (3414 words).
Version 2 · May 18, 2026, 08:30 AM