We'll know we hit ASI when we judge models by the questions they ask
matanSF · x · 2026-09-26
A widely shared one-liner in AI circles: the author argues we'll know we've hit ASI when we start measuring model intelligence by the questions they ask rather than the answers they give.
More from Fun
- Matt Pocock: haven't needed /wait-what since 5.5 shipped — mattpocockuk · 2026-09-26
- Pixar's 4-Minute-18-Second Silent Montage Engineered Audiences to Side With an Assailant in Up — aakashgupta · 2026-09-26
- Claude made a music video for a user's song — and it's "insane" — AndyMasley · 2026-09-26
- Someone is Playing Among Us With LLMs and Promises a Video Soon — i_dg23 · 2026-09-26
- UK Government Publishes Official Rules for Civil Servants' AI Use, Gets Mocked — alejandroll10 · 2026-09-26
- Fan 3D-prints orange hair clips for a Claude maker dinner — floguo · 2026-09-26