GPT-6 fails to improve on molecular property prediction, fueling AGI skepticism
GaryMarcus · x · 2026-09-12
Echoing Gary Marcus, Rim Shayakhmetov argues GPT-6 can't be called AGI when even a non-novel scientific task like molecular property prediction isn't solved and shows no improvement over prior versions: some level of pharmaceutical intelligence has to happen before AGI.
More from Models
- Zed founder shows one link task eating ~50% of Claude subscription quota — zeeg · 2026-09-12
- Demo claims precise camera control with GPT-6 Astra (unverified) — round · 2026-09-12
- Burkov: Visual Reasoning Still Trails Luna and Gemini Flash — burkov · 2026-09-12
- Burkov on RL Whack-a-Mole: Fix One Failure, Another Pops Up — burkov · 2026-09-12
- GPT-Live-1 listens and speaks at once, shifting AI from prompts to live collaboration — WirelessLife · 2026-09-12
- Evals are increasingly unreadable: overly strict hidden tests mislabel good answers — trq212 · 2026-09-12