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.

Related event: Burkov: Models Still Sycophantic; Without Harness, Intelligence on Par with o1(2 posts)→

Original post →

More from Models

Models channel →