GPT-5.2 Pro solves COLT 2022 open problem on accelerated L1-regularized PageRank
kfountou · x · 2026-11-08
Researcher kfountou reports GPT-5.2 solved their COLT 2022 open problem on the running-time complexity of accelerated L1-regularized PageRank, with all proofs generated by GPT-5.2 Pro and key bounds auto-formalized to Lean using GPT-5.2 Pro, Harmonic's Aristotle, and Gemini 3 Pro (High) on Antigravity. They also used Gemini 2.5 Pro in summer 2025 for theory work published at COLT 2026, and defend ML conference peer review, noting nearly all their ICML/NeurIPS/ICLR submissions were accepted.
More from AGI Musings
- Pascal Bornet coins 'AI Obesity': asking AI what to think erodes your judgment — sanderssays · 2026-11-08
- DHH: Agents Bring Back the Commodore 64 Era of Computing Invitation — mark_k · 2026-11-08
- AI Safety Researcher Pivots From Preaching Short Timelines to Questioning the Evidence — JacquesThibs · 2026-11-08
- YC Paper Club: AI for Biology, From Reading Data to Designing Living Systems — ycombinator · 2026-11-08
- Nina Schick: AI is industrialising intelligence, echoing the Industrial Revolution's escape from Malthusian trap — NinaDSchick · 2026-11-08
- Daniel Faggella: positive AGI outcomes require governance, not saintly leaders — danfaggella · 2026-11-08