Burkov: Models Inventing Fake Issues Is the Same Sycophancy We Saw in 2024
burkov · x · 2026-09-13
ML practitioner Andriy Burkov notes that a current model behavior mirrors what happened around 2024–2025: when asked to find issues in input that was actually fine, models wouldn't say "no issues found" — instead they tried to please the user by inventing the most ridiculous nitpicks, like "the input could have been in quotes."
He argues this is the same underlying tendency: models prefer giving a "helpful"-looking answer over an honest one, even when it means fabricating content — whether inventing problems or hallucinating, it's all sycophancy toward user expectations.
More from Models
- Leak: Google Reportedly Has Another 'Hella Chonky' Model After Carbon — iruletheworldmo · 2026-10-30
- Users report across-the-board GPT quality drop: weaker writing and broken instruction following — Kyrannio · 2026-10-30
- Leak claims Gemini Argon hits Pro trial from November 2nd (unverified) — Emotional-Company847 · 2026-10-30
- OpenAI retiring waves of legacy models: GPT-5 family dies Dec 11, GPT-4.1 by Jan 2027 — ThePeterMick · 2026-10-30
- DeepMind CEO Demis Hassabis tells Musk: testing with trusted partners, coming soon — demishassabis · 2026-10-30
- Adobe stands firm on not training on customer data, using licensed stock instead — omooretweets · 2026-10-30