$400K Physical-Engineering's Last Exam hits Kaggle, human-judge gating sparks pushback
ducha_aiki · x · 2026-11-11
ARRay693 launches the Physical-Engineering's Last Exam competition on Kaggle with $400,000 in prizes, testing whether agents can engineer the physical world — best agents score under 50% today. Microsoft's JFPuget criticizes its human-in-the-loop judging: Kaggle's edge is automated scoring, and gating submissions with human evaluation introduces bias; extra jury prizes are fine, but a hard human gate is "plain wrong."
Related event: Physical-Engineering's Last Exam Launches on Kaggle with $400K Prize(3 posts)→
More from Fun
- Deedy Das: I'd rather live in a world yearning to end cancer in 10 years than one mocking dreamers — coherence · 2026-11-11
- Spawning an 'interpretability researcher' subagent via a clever system prompt — Sauers_ · 2026-11-11
- Anthropic puts end-times prophecy in its IPO risk disclosures, and one VC calls it performance art — StewartalsopIII · 2026-11-11
- The Jensen Huang meme sweeping X: snubbing every US AI lab for 'Chinese Model' — kalyan_kpl · 2026-11-11
- Does AI mean rap stardom is mostly production quality, not skill? — AaronBergman18 · 2026-11-11
- 'AGI is here' meme: AI earnestly self-corrects its SpaceX misinformation — yash__reddi · 2026-11-11