A reply says ARC-AGI is not AGI, even as better AIs keep pushing the field forward
Dr_Singularity · x · 2026-07-25
In a reply to Demis Hassabis, the poster says they usually comment that we are getting closer to AGI as AIs improve, but adds that ARC-AGI has nothing to do with AGI.
The exchange is a compact example of the recurring debate over whether benchmark progress should be treated as evidence of general intelligence.
Related event: Opus 5's High ARC-AGI-3 Score Sparks Cheating and Overfitting Controversy(11 posts)→
More from AGI Musings
- Instinct launches agent-to-agent protocol to coordinate your plans, sparking 'friction is the point' backlash — itsOmSarraf_ · 2026-09-11
- We are witnessing the unreasonable effectiveness of inference-time scaling — sqcai · 2026-09-11
- Accelerationist fires back at AI doomers: beliefs aren't arguments — Dan_Jeffries1 · 2026-09-11
- "ChatGPT 6 Makes Workers with IQ Below 130 Useless": French AI Debate Sparks Backlash — mitchdeg · 2026-09-11
- 'AGI is here' vs reality: AI labs still ship some of the jankiest desktop apps ever — MilesCranmer · 2026-09-11
- Harry Collins: LLMs can't do frontier science because they can't invent new language — whoamisri · 2026-09-11