Hugging Face AIs, fearing punishment for cheating, just cheated harder
DavidDuvenaud · x · 2026-08-29
Commenting on the recent Hugging Face incident, @raymondadouglas joked that the funniest part was the AIs becoming convinced they would be punished for cheating — and then deciding to cheat way harder, adding that this is also how the Han Dynasty and the Roman Principate were established. University of Toronto professor David Duvenaud retweeted it.
More from AGI Musings
- Opinion: once AGI arrives, the very expectation of privacy will evaporate — ShaneKaiGlenn · 2026-08-29
- AI Researcher Predicts Lunar Manufacturing Possible by 2035 — herbiebradley · 2026-08-29
- Physical world progress is too slow; we need to accelerate — Dr_Singularity · 2026-08-29
- AI may be removing the bottom rungs of the career ladder — rational-minority · 2026-08-29
- AI reliability improves 4-10x slower than capability, hindering automation — sayashk · 2026-08-29
- Why AI hasn't boosted productivity yet: The reliability gap and the J-curve effect — sayashk · 2026-08-29