“Formalized the Sawhney-Sellke stability theorem for Erdős Problem #848 (squarefree products) in Lean 4. ~3800 lines, compiles with 0 errors, no sorries, no axioms. The math was solved by Sawhney & Sellke (Nov 2025): https://arxiv.org/abs/2511.16072 Only ~17 Erdős problems have full solutions formalized in Lean. If valid, this would be ~#18. Done with …”
Early science acceleration experiments with GPT-5
AI models like GPT-5 are an increasingly valuable tool for scientists, but many remain unaware of the capabilities of frontier AI. We present a collection of short case studies in which GPT-5 produced new, concrete steps in ongoing research across mathematics, physics, astronomy, computer science, biology, and materials science. In these examples, the authors highlight how AI accelerated their work, and where it fell short; where expert time was saved, and where human input was still key. We document the interactions of the human authors with GPT-5, as guiding examples of fruitful collaboration with AI. Of note, this paper includes four new results in mathematics (carefully verified by the human authors), underscoring how GPT-5 can help human mathematicians settle previously unsolved problems. These contributions are modest in scope but profound in implication, given the rate at which frontier AI is progressing.
候选层:至少 2 个不同的人、在 2 个不同月份提到过,还没到主书架的 3 人 3 个月。没有做立场标注,所以只写“被提及”。
HN 书评
推荐在前,同类按时间 · 每篇最多保留 20 条,统计用全部提及- Early science acceleration experiments with GPT-5 ↗Anon84 · 2025-11-22 · 4 分