--- title: Baking a Model | daily.dev description: Kent Beck reflects on his fascination with how AI models are built, using a baking analogy to explain pre-training and post-training. Pre-training is described... canonical: https://daily.dev/posts/baking-a-model-2pfmlmzyh twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Baking a Model | daily.dev og:description: Kent Beck reflects on his fascination with how AI models are built, using a baking analogy to explain pre-training and post-training. Pre-training is described... og:url: https://daily.dev/posts/baking-a-model-2pfmlmzyh og:image: https://api.daily.dev/og/posts/2PFmlMzyH.png og:image:alt: Baking a Model 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. # Baking a Model **[Software Design: Tidy First?](https://daily.dev/sources/tidyfirst)** · 5 min read · 1 upvotes · 0 comments ## Summary Kent Beck reflects on his fascination with how AI models are built, using a baking analogy to explain pre-training and post-training. Pre-training is described as a massive, expensive, one-shot batch process (akin to cold proofing dough) that produces raw, unusable model weights, while post-training is an iterative, collaborative series of small tweaks (the shaping and baking) that turns the raw model into something useful for humans. The piece is exploratory and speculative, framed as the author's attempt to understand the process, with a promise of a followup on the teams and roles involved. Ends with a promotional pitch for the author's advisory and speaking services. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### What is the difference between pre-training and post-training in AI language models? Pre-training is a single large batch process where a team sets initial conditions, data, and a blank model, then runs data through it repeatedly over months at a cost of hundreds of millions of dollars, producing a raw but unusable base model. Post-training consists of many small, iterative batches where researchers target specific weaknesses in the raw model with small chunks of code and data, gradually shaping it into something that responds usefully to prompts. _Developers piecing together how model training actually works can find grounded explainers like this through daily.dev._ ## Similar posts on daily.dev - [Machine Learning Blog \| ML@CMU \| Carnegie Mellon University](https://daily.dev/posts/machine-learning-blog-ml-cmu-carnegie-mellon-university-yhdqaje8i) · ML CMU · 24 upvotes · 0 comments --- Tags: [#ai](https://daily.dev/tags/ai), [#machine-learning](https://daily.dev/tags/machine-learning), [#llm](https://daily.dev/tags/llm) [View this post on daily.dev](https://daily.dev/posts/baking-a-model-2pfmlmzyh) ```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":"Baking a Model","url":"https://daily.dev/posts/baking-a-model-2pfmlmzyh","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/baking-a-model-2pfmlmzyh"},"datePublished":"2026-08-14T13:41:53.749Z","dateModified":"2026-09-14T07:30:10.526Z","description":"Kent Beck reflects on his fascination with how AI models are built, using a baking analogy to explain pre-training and post-training. Pre-training is described...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/eb4a0b5ceca3a877d89db6f7ae4f80b4?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/eb4a0b5ceca3a877d89db6f7ae4f80b4?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"Software Design: Tidy First?","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":"Software Design: Tidy First?","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/dfed97125daa47dda66c4df89430c08c","url":"https://daily.dev/sources/tidyfirst"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/baking-a-model-2pfmlmzyh","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":1},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"ai,machine-learning,llm","timeRequired":"PT5M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Software Design: Tidy First?","item":"https://daily.dev/sources/tidyfirst"},{"@type":"ListItem","position":3,"name":"Baking a Model"}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/baking-a-model-2pfmlmzyh#faq","mainEntity":[{"@type":"Question","name":"What is the difference between pre-training and post-training in AI language models?","acceptedAnswer":{"@type":"Answer","text":"Pre-training is a single large batch process where a team sets initial conditions, data, and a blank model, then runs data through it repeatedly over months at a cost of hundreds of millions of dollars, producing a raw but unusable base model. Post-training consists of many small, iterative batches where researchers target specific weaknesses in the raw model with small chunks of code and data, gradually shaping it into something that responds usefully to prompts. Developers piecing together how model training actually works can find grounded explainers like this through daily.dev."}}]} ```