--- title: Training Language Models via Neural Cellular Automata description: Researchers propose using Neural Cellular Automata (NCA) as a synthetic pre-pre-training data source for language models, bypassing the need for natural... canonical: https://daily.dev/posts/training-language-models-via-neural-cellular-automata-sg0rcdmbq twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Training Language Models via Neural Cellular Automata | daily.dev og:description: Researchers propose using Neural Cellular Automata (NCA) as a synthetic pre-pre-training data source for language models, bypassing the need for natural... og:url: https://daily.dev/posts/training-language-models-via-neural-cellular-automata-sg0rcdmbq og:image: https://api.daily.dev/og/posts/sG0rcDMbq.png og:image:alt: Training Language Models via Neural Cellular Automata 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. # Training Language Models via Neural Cellular Automata **[Hacker News](https://daily.dev/sources/hn)** · 4 min read · 2 upvotes · 0 comments ## Summary Researchers propose using Neural Cellular Automata (NCA) as a synthetic pre-pre-training data source for language models, bypassing the need for natural language text. NCA trajectories — generated by randomly sampled neural networks acting as transition rules on a grid — are tokenized and used to train transformers via next-token prediction. With only 164M tokens, NCA pre-pre-training outperforms training on natural language (C4) and other synthetic data across web text, math, and code benchmarks. Even when C4 is given 10× more data (1.6B tokens), NCA still converges 1.4× faster and achieves 5% better final perplexity. The key mechanism: NCA sequences contain no semantic shortcuts, forcing models to develop in-context rule inference and robust induction heads in attention layers. Optimal NCA complexity varies by target domain, offering a new lever for targeted, compute-efficient training. The long-term vision is foundation models that acquire reasoning from fully synthetic data before learning semantics from a small curated corpus. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Similar posts on daily.dev - [Seeing sounds](https://daily.dev/posts/seeing-sounds-lko2p1khm) · MIT News · 0 upvotes · 0 comments --- Tags: [#llm](https://daily.dev/tags/llm) [View this post on daily.dev](https://daily.dev/posts/training-language-models-via-neural-cellular-automata-sg0rcdmbq) ```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":"Training Language Models via Neural Cellular Automata","url":"https://daily.dev/posts/training-language-models-via-neural-cellular-automata-sg0rcdmbq","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/training-language-models-via-neural-cellular-automata-sg0rcdmbq"},"datePublished":"2026-03-19T18:05:33.396Z","dateModified":"2026-03-19T18:05:53.717Z","description":"Researchers propose using Neural Cellular Automata (NCA) as a synthetic pre-pre-training data source for language models, bypassing the need for natural...","image":"https://media.daily.dev/image/upload/s--OHB84bZF--/f_auto/v1722860399/public/Placeholder%2010","thumbnailUrl":"https://media.daily.dev/image/upload/s--OHB84bZF--/f_auto/v1722860399/public/Placeholder%2010","isAccessibleForFree":true,"articleSection":"Hacker News","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":"Hacker News","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/hn","url":"https://daily.dev/sources/hn"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/training-language-models-via-neural-cellular-automata-sg0rcdmbq","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":2},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"llm","timeRequired":"PT4M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Hacker News","item":"https://daily.dev/sources/hn"},{"@type":"ListItem","position":3,"name":"Training Language Models via Neural Cellular Automata"}]} ```