After p-hacking, the AI crowd coins "O-hacking" for gaming benchmarks
chrisalbon · x · 2026-10-13
Borrowing from statistics' p-hacking, users coined "O-hacking" to joke that OpenAI games its own evals. A meme, but it reflects ongoing skepticism about frontier labs manipulating benchmark scores.
More from Fun
- Google AI Overviews denied a person had died, renewing criticism of AIO for news — lilyraynyc · 2026-10-13
- Two camps in SWE: will superintelligent AI write machine code or JavaScript? — wordgrammer · 2026-10-13
- User feeds Claude Opus GTA frame-by-frame screenshots since it can't watch videos — adonis_singh · 2026-10-13
- Zuck's watermelon meme is his answer to calls to slow down frontier AI — beffjezos · 2026-10-13
- Kurzgesagt's OpenAI-Hugging Face incident video hits 18.4M views in one week — NathanpmYoung · 2026-10-13
- Joke: Anthropic security team will nuke something with GLM 6 to prove open weights are dangerous — mimi10v3 · 2026-10-13