--- title: DeepMind’s New AI Found A Strange New Way To Think description: DeepMind's AlphaProof Nexus solved 9 out of 350 long-standing Erdős mathematical problems by combining an AI agent with a formal proof checker (Lean) and a... canonical: https://daily.dev/posts/deepmind-s-new-ai-found-a-strange-new-way-to-think-gqwtdmc0u twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: DeepMind’s New AI Found A Strange New Way To Think | daily.dev og:description: DeepMind's AlphaProof Nexus solved 9 out of 350 long-standing Erdős mathematical problems by combining an AI agent with a formal proof checker (Lean) and a... og:url: https://daily.dev/posts/deepmind-s-new-ai-found-a-strange-new-way-to-think-gqwtdmc0u og:image: https://api.daily.dev/og/posts/GQwtdmC0U.png og:image:alt: DeepMind’s New AI Found A Strange New Way To Think og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # DeepMind’s New AI Found A Strange New Way To Think **[Two Minute Papers](https://daily.dev/sources/twoninutepapers)** · 7 min read · 1 upvotes · 0 comments ## Summary DeepMind's AlphaProof Nexus solved 9 out of 350 long-standing Erdős mathematical problems by combining an AI agent with a formal proof checker (Lean) and a tournament-style ELO ranking loop. Rather than making the AI smarter, the key innovation is the harness around it: a cheap judge AI picks the better of two flawed solutions, scores proofs like chess players, and iterates from the best bad solution until a valid proof emerges. This approach builds a reliable system from unreliable parts. Limitations include selection bias in the 350-problem subset and the requirement for large frontier models — smaller models solved zero problems. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Similar posts on daily.dev - [DeepMind’s latest: An AI for handling mathematical proofs](https://daily.dev/posts/deepmind-s-latest-an-ai-for-handling-mathematical-proofs-p88dclgu1) · Ars Technica · 3 upvotes · 0 comments - [Mathematical Experiments Are Becoming Abundant Through Human-Machine Teaming](https://daily.dev/posts/mathematical-experiments-are-becoming-abundant-through-human-machine-teaming-at6d9wesn) · Towards Data Science · 1 upvotes · 0 comments - [Terence Tao: "Recently, the application of A…"](https://daily.dev/posts/terence-tao-recently-the-application-of-a--uqsiau1lp) · Hacker News · 1 upvotes · 0 comments --- Tags: [#ai](https://daily.dev/tags/ai), [#llm](https://daily.dev/tags/llm), [#ai-agents](https://daily.dev/tags/ai-agents) [View this post on daily.dev](https://daily.dev/posts/deepmind-s-new-ai-found-a-strange-new-way-to-think-gqwtdmc0u) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"DeepMind’s New AI Found A Strange New Way To Think","url":"https://daily.dev/posts/deepmind-s-new-ai-found-a-strange-new-way-to-think-gqwtdmc0u","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/deepmind-s-new-ai-found-a-strange-new-way-to-think-gqwtdmc0u"},"datePublished":"2026-06-05T16:16:36.948Z","dateModified":"2026-06-05T16:16:56.581Z","description":"DeepMind's AlphaProof Nexus solved 9 out of 350 long-standing Erdős mathematical problems by combining an AI agent with a formal proof checker (Lean) and a...","image":"https://i.ytimg.com/vi/Dkqzqw8rxXI/sddefault.jpg","thumbnailUrl":"https://i.ytimg.com/vi/Dkqzqw8rxXI/sddefault.jpg","isAccessibleForFree":true,"articleSection":"Two Minute Papers","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"Two Minute Papers","logo":"https://media.daily.dev/image/upload/s--8KXsSJ5q--/f_auto/v1711188923/logos/twoninutepapers","url":"https://daily.dev/sources/twoninutepapers"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/deepmind-s-new-ai-found-a-strange-new-way-to-think-gqwtdmc0u","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":1},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"ai,llm,ai-agents","timeRequired":"PT7M","video":{"@type":"VideoObject","name":"DeepMind’s New AI Found A Strange New Way To Think","description":"DeepMind's AlphaProof Nexus solved 9 out of 350 long-standing Erdős mathematical problems by combining an AI agent with a formal proof checker (Lean) and a...","thumbnailUrl":"https://i.ytimg.com/vi/Dkqzqw8rxXI/sddefault.jpg","uploadDate":"2026-06-05T16:16:36.948Z","duration":"PT7M","url":"https://api.daily.dev/r/GQwtdmC0U","embedUrl":"https://www.youtube.com/embed/Dkqzqw8rxXI"}} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Two Minute Papers","item":"https://daily.dev/sources/twoninutepapers"},{"@type":"ListItem","position":3,"name":"DeepMind’s New AI Found A Strange New Way To Think"}]} ```