Joke: labs will soon use time-to-prove-the-Riemann-hypothesis as a benchmark
khademinori · x · 2026-11-22
A quoted tweet predicts that in six to twelve months, frontier labs will use time-to-prove-the-Riemann-hypothesis as a benchmark to show off model capabilities, with around five independent models able to do it. The poster jokes this will be "the new MNIST."
More from Fun
- Honeypot catches Tencent crawler disguised as iPhone ignoring robots.txt to steal fake API key — rickasaurus · 2026-11-22
- OpenRouter's new BYOK transparency feature clears Hy4 'fake volume' suspicion: traffic was from OpenCode — gajesh · 2026-11-22
- Gary Marcus's 2024 post resurfaces as AI community mocks his aged prediction — AIandDesign · 2026-11-22
- DeepMind's Samuel Albanie opens a bet on how many Millennium Prize Problems get solved by Jan 2027 — SamuelAlbanie · 2026-11-22
- Browser dragon-in-your-hand demo built with Three.js, MediaPipe hand tracking and WebRTC — techartist_ · 2026-11-22
- Wenhu Chen Revives 'But Can They Reason?' Debate, Asking Why Critics Went Silent — WenhuChen · 2026-11-22