--- title: Mr. Chatterbox is a (weak) Victorian-era ethically... description: Trip Venturella released Mr. Chatterbox, a 340M-parameter language model trained from scratch on 28,035 Victorian-era British Library texts (2.93B tokens, all... canonical: https://daily.dev/posts/mr-chatterbox-is-a-weak-victorian-era-ethically-trained-model-you-can-run-on-your-own-computer-bbv4egfg4 twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Mr. Chatterbox is a (weak) Victorian-era ethically trained model you can run on your own computer | daily.dev og:description: Trip Venturella released Mr. Chatterbox, a 340M-parameter language model trained from scratch on 28,035 Victorian-era British Library texts (2.93B tokens, all... og:url: https://daily.dev/posts/mr-chatterbox-is-a-weak-victorian-era-ethically-trained-model-you-can-run-on-your-own-computer-bbv4egfg4 og:image: https://api.daily.dev/og/posts/BBv4eGFg4.png og:image:alt: Mr. Chatterbox is a (weak) Victorian-era ethically trained model you can run on your own computer 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. # Mr. Chatterbox is a (weak) Victorian-era ethically trained model you can run on your own computer **[Simon Willison](https://daily.dev/sources/simonwillison)** · 5 min read · 0 upvotes · 0 comments ## Summary Trip Venturella released Mr. Chatterbox, a 340M-parameter language model trained from scratch on 28,035 Victorian-era British Library texts (2.93B tokens, all pre-1900). Simon Willison explores the model, noting it performs poorly — more like a Markov chain than a modern LLM — likely because the training data is less than half what the Chinchilla scaling law recommends. Willison used Claude Code to build an LLM plugin (llm-mrchatterbox) enabling local execution via simple CLI commands. A key caveat: the supervised fine-tuning used synthetic conversation pairs generated by Claude Haiku and GPT-4o-mini, undermining the 'no post-1899 inputs' claim. Despite its limitations, the project is seen as a promising step toward useful models trained entirely on public domain data. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: --- Tags: [#machine-learning](https://daily.dev/tags/machine-learning), [#llm](https://daily.dev/tags/llm), [#claude-code](https://daily.dev/tags/claude-code) [View this post on daily.dev](https://daily.dev/posts/mr-chatterbox-is-a-weak-victorian-era-ethically-trained-model-you-can-run-on-your-own-computer-bbv4egfg4) ```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":"Mr. Chatterbox is a (weak) Victorian-era ethically trained model you can run on your own computer","url":"https://daily.dev/posts/mr-chatterbox-is-a-weak-victorian-era-ethically-trained-model-you-can-run-on-your-own-computer-bbv4egfg4","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/mr-chatterbox-is-a-weak-victorian-era-ethically-trained-model-you-can-run-on-your-own-computer-bbv4egfg4"},"datePublished":"2026-04-07T18:01:20.242Z","dateModified":"2026-04-07T18:05:02.242Z","description":"Trip Venturella released Mr. Chatterbox, a 340M-parameter language model trained from scratch on 28,035 Victorian-era British Library texts (2.93B tokens, all...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/6581a26191576a8210bdaca578524123?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/6581a26191576a8210bdaca578524123?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"Simon Willison","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":"Simon Willison","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/cf12b897300740218b35f49a6309ec5b","url":"https://daily.dev/sources/simonwillison"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/mr-chatterbox-is-a-weak-victorian-era-ethically-trained-model-you-can-run-on-your-own-computer-bbv4egfg4","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"machine-learning,llm,claude-code","timeRequired":"PT5M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Simon Willison","item":"https://daily.dev/sources/simonwillison"},{"@type":"ListItem","position":3,"name":"Mr. Chatterbox is a (weak) Victorian-era ethically trained model you can run on your own computer"}]} ```