Viral claim that AI math reasoning is 'middle-school level' traced to a 1.5-year-old video
oran_ge · x · 2026-10-25
Blogger orange shared a moment of relief: a video claiming AI is decent at humanities but only at middle-school level in mathematical logic turned out to be 1.5 years old, as he confirmed by checking the timestamp. The screenshot shows a Bilibili career guide listing 'deep reasoning' as an AI weakness. A reminder that AI capability commentary goes stale fast.
More from AGI Musings
- AI agent books an impossible cardiologist appointment through Goa's broken portal — alysha_lobo · 2026-10-25
- There's no moat in code anymore: what's left is distribution, taste, community — paw_lean · 2026-10-25
- Cartoon skewers AI alignment: chained robots taught "human values" in a classroom — repligate · 2026-10-25
- Copywriters most AI-anxious at 33%, engineers near 24% — job worry survey ranks top 10 — oran_ge · 2026-10-25
- One year ago, entrepreneurs topped the 'least worried about AI' poll at 83% — oran_ge · 2026-10-25
- AI fixes 95.8% of failed spinal-cord labels: nnU-Net rescues patient MRI data — bravo_abad · 2026-10-25