Model agrees with user = sycophancy, agrees with lab = alignment
louisvarge · x · 2026-11-03
A widely shared quip in AI circles: when a model agrees with the user it's labeled "sycophancy," but when it agrees with the lab it's called "alignment" — pointing at the definitional double standard in how the industry judges model behavior.
More from AGI Musings
- Anthropic warns it is very close to RSI capability, aka self-building AI — TechCrunch AI · 2026-11-03
- 'Recursive self degeneration': AI that gets more powerful while making worse decisions — cocktailpeanut · 2026-11-03
- Very few people treat the future as construction rather than prediction — signulll · 2026-11-03
- Researcher: alignment will be solved the bitter-lesson way, not via human enhancement — tszzl · 2026-11-03
- Under 1T params already superhuman — AI models aren't underparametrized, argues researcher — teortaxesTex · 2026-11-03
- Psychics push back as AI-generated readings flood apps and TikTok Live — Chris_Armstrong · 2026-11-03