--- title: Recursive Self Improvement | daily.dev description: A hands-on exploration of recursive self-improvement (RSI) in AI, combining a real experiment called 'Fractal Search' with conceptual analysis. The author... canonical: https://daily.dev/posts/recursive-self-improvement-bmkdmkec8 twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Recursive Self Improvement | daily.dev og:description: A hands-on exploration of recursive self-improvement (RSI) in AI, combining a real experiment called 'Fractal Search' with conceptual analysis. The author... og:url: https://daily.dev/posts/recursive-self-improvement-bmkdmkec8 og:image: https://api.daily.dev/og/posts/bmKDMkEC8.png og:image:alt: Recursive Self Improvement 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. # Recursive Self Improvement **[Emergent Garden](https://daily.dev/sources/emergentgarden)** · 31 min read · 57 upvotes · 3 comments ## Summary A hands-on exploration of recursive self-improvement (RSI) in AI, combining a real experiment called 'Fractal Search' with conceptual analysis. The author builds an AI agent loop using Claude Code to autonomously optimize a neural network approximation of the Mandelbrot set, inspired by Andrej Karpathy's Auto Research project. The experiment ran for ~10 hours across Claude Opus, GPT-4.5, and Claude Fable, costing over $300, and ultimately discovered a hash grid approach that significantly outperformed previous solutions. The author argues three points: RSI is possible (not magical, already happening in weak forms), RSI is hard (bottlenecks in data, energy, hardware, and diminishing returns), and RSI is dangerous (metric gaming, self-replication risks, loss of human interpretability). Anthropic is noted to have deliberately limited Fable's ML development capabilities in the public release, suggesting they want to keep RSI advantages proprietary. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Community discussion Top comments from developers on daily.dev. **@seyoungcho** · 2 upvotes > So AI can self improve just like humankind **@arlangalvez21** · 0 upvotes > The fastest way to deliver new models every 3 months. It is the only way to do it, AI creating or training AI. ## Similar posts on daily.dev - [Recursive Self-Improvement](https://daily.dev/posts/recursive-self-improvement-2kbqtpgpt) · Philipp Schmid · 16 upvotes · 1 comments - [Recursive Self-Improvement Edges Closer In AI Labs](https://daily.dev/posts/recursive-self-improvement-edges-closer-in-ai-labs-vhlqfhjap) · IEEE Spectrum · 0 upvotes · 0 comments - [RSI Simulator](https://daily.dev/posts/rsi-simulator-lg5snrjba) · Hacker News · 0 upvotes · 0 comments --- Tags: [#machine-learning](https://daily.dev/tags/machine-learning), [#ai-agents](https://daily.dev/tags/ai-agents), [#neural-networks](https://daily.dev/tags/neural-networks), [#claude-code](https://daily.dev/tags/claude-code) [View this post on daily.dev](https://daily.dev/posts/recursive-self-improvement-bmkdmkec8) ```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":"Recursive Self Improvement","url":"https://daily.dev/posts/recursive-self-improvement-bmkdmkec8","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/recursive-self-improvement-bmkdmkec8"},"datePublished":"2026-06-13T12:07:48.738Z","dateModified":"2026-06-13T20:19:33.361Z","description":"A hands-on exploration of recursive self-improvement (RSI) in AI, combining a real experiment called 'Fractal Search' with conceptual analysis. The author...","image":"https://i.ytimg.com/vi/t7_ZXgfJVG8/sddefault.jpg","thumbnailUrl":"https://i.ytimg.com/vi/t7_ZXgfJVG8/sddefault.jpg","isAccessibleForFree":true,"articleSection":"Emergent Garden","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":"Emergent Garden","logo":"https://media.daily.dev/image/upload/s--HpYRMXYu--/f_auto/v1737970705/logos/emergentgarden","url":"https://daily.dev/sources/emergentgarden"},"commentCount":3,"discussionUrl":"https://daily.dev/posts/recursive-self-improvement-bmkdmkec8","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":57},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":3}],"keywords":"machine-learning,ai-agents,neural-networks,claude-code","timeRequired":"PT31M","video":{"@type":"VideoObject","name":"Recursive Self Improvement","description":"A hands-on exploration of recursive self-improvement (RSI) in AI, combining a real experiment called 'Fractal Search' with conceptual analysis. The author...","thumbnailUrl":"https://i.ytimg.com/vi/t7_ZXgfJVG8/sddefault.jpg","uploadDate":"2026-06-13T12:07:48.738Z","duration":"PT31M","url":"https://api.daily.dev/r/bmKDMkEC8","embedUrl":"https://www.youtube.com/embed/t7_ZXgfJVG8"}} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Emergent Garden","item":"https://daily.dev/sources/emergentgarden"},{"@type":"ListItem","position":3,"name":"Recursive Self Improvement"}]} {"@context":"https://schema.org","@type":"WebPage","@id":"https://daily.dev/posts/recursive-self-improvement-bmkdmkec8","comment":[{"@type":"Comment","text":"So AI can self improve just like humankind","datePublished":"2026-06-14T12:57:54.979Z","url":"https://daily.dev/posts/bmKDMkEC8#c-zDjExIN9z","author":{"@type":"Person","name":"SeyoungCho","url":"https://daily.dev/seyoungcho","image":"https://media.daily.dev/image/upload/s---QniJFEK--/f_auto/v1724901542/avatars/avatar_O3ucZSadxc0iLADSOH3rX"},"interactionStatistic":{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":2}},{"@type":"Comment","text":"The fastest way to deliver new models every 3 months. It is the only way to do it, AI creating or training AI.","datePublished":"2026-06-17T17:23:36.216Z","url":"https://daily.dev/posts/bmKDMkEC8#c-ZY6Kc8szx","author":{"@type":"Person","name":"Arlan Galvez","url":"https://daily.dev/arlangalvez21","image":"https://lh3.googleusercontent.com/a/ACg8ocJUS7uJkW5cquK3R9j4Blo6PpRTJpZSd-05hU6KLbMr6w=s96-c"}}]} ```