Benchmark saturation accelerates: ARC-AGI-3 falls in 5 months after ARC-AGI-1's 6 years
mmmbchang · x · 2026-09-04
LiuZuxin notes how fast frontier benchmarks now saturate: ARC-AGI-1 took 6 years to crack, ARC-AGI-2 took 16 months, and ARC-AGI-3 just 5 months. The frontier is moving faster than benchmarks can be designed and saturated.
More from AGI Musings
- Jim Fan on World of Bits: OpenAI's 2016 booking-agent dream finally realized by GPT-6 — DrJimFan · 2026-09-04
- The bitterest lesson: your production job is their ablation — vedantmisra · 2026-09-04
- Neel Nanda Defends CoT Monitoring as Safety Tool; Critics Cite Faithfulness Gaps — AlexTensor · 2026-09-04
- Paul Graham: AGI Isn't a Finish Line, It's a Smear — and We're Already On It — garrytan · 2026-09-04
- What does 'most aligned model' even mean? AI circle debates the definition — sandersted · 2026-09-04
- Developer: most people and most developers hate AI — X is a tiny bubble — kylegawley · 2026-09-04