[{"data":1,"prerenderedAt":229},["ShallowReactive",2],{"navigation_docs_en":3,"\u002Fen\u002Fai-engineering\u002Fintro\u002Fch01":46,"\u002Fen\u002Fai-engineering\u002Fintro\u002Fch01-surround":226},[4],{"title":5,"icon":6,"path":7,"stem":8,"children":9,"page":45},"AI Engineering",null,"\u002Fen\u002Fai-engineering","en\u002F1.ai-engineering",[10],{"title":11,"icon":12,"path":13,"stem":14,"children":15,"page":45},"Introduction to Building AI Applications with Foundation Models","i-lucide-brain-circuit","\u002Fen\u002Fai-engineering\u002Fintro","en\u002F1.ai-engineering\u002F1.intro",[16,20,25,30,35,40],{"title":11,"path":17,"stem":18,"icon":19},"\u002Fen\u002Fai-engineering\u002Fintro\u002Fch01","en\u002F1.ai-engineering\u002F1.intro\u002Fch01","i-lucide-sparkles",{"title":21,"path":22,"stem":23,"icon":24},"The Rise of AI Engineering","\u002Fen\u002Fai-engineering\u002Fintro\u002Fch011-the-rise-of-ai-engineering","en\u002F1.ai-engineering\u002F1.intro\u002Fch011-the-rise-of-ai-engineering","i-lucide-history",{"title":26,"path":27,"stem":28,"icon":29},"Foundation Model Use Cases","\u002Fen\u002Fai-engineering\u002Fintro\u002Fch012-foundation-model-use-cases","en\u002F1.ai-engineering\u002F1.intro\u002Fch012-foundation-model-use-cases","i-lucide-layout-grid",{"title":31,"path":32,"stem":33,"icon":34},"Planning AI Applications","\u002Fen\u002Fai-engineering\u002Fintro\u002Fch013-planning-ai-applications","en\u002F1.ai-engineering\u002F1.intro\u002Fch013-planning-ai-applications","i-lucide-clipboard-list",{"title":36,"path":37,"stem":38,"icon":39},"The AI Engineering Stack","\u002Fen\u002Fai-engineering\u002Fintro\u002Fch014-the-ai-engineering-stack","en\u002F1.ai-engineering\u002F1.intro\u002Fch014-the-ai-engineering-stack","i-lucide-layers",{"title":41,"path":42,"stem":43,"icon":44},"Summary","\u002Fen\u002Fai-engineering\u002Fintro\u002Fch015-summary","en\u002F1.ai-engineering\u002F1.intro\u002Fch015-summary","i-lucide-flag",false,{"id":47,"title":11,"body":48,"description":220,"extension":221,"links":6,"meta":222,"navigation":223,"path":17,"seo":224,"stem":18,"__hash__":225},"docs_en\u002Fen\u002F1.ai-engineering\u002F1.intro\u002Fch01.md",{"type":49,"value":50,"toc":208},"minimark",[51,79,84,88,110,114,117,137,141,144,158,166,170,200],[52,53,54,59,67],"u-page-hero",{},[55,56,58],"template",{"v-slot:title":57},"","The Age of Scale",[55,60,61,62,66],{"v-slot:description":57},"If I could use only one word to describe AI post-2020, it'd be ",[63,64,65],"strong",{},"scale",". The models behind ChatGPT, Gemini, and Midjourney are at such a scale that they're consuming a nontrivial portion of the world's electricity — and we're at risk of running out of publicly available internet data to train them.",[55,68,69],{"v-slot:links":57},[70,71,78],"u-button",{"color":72,"icon":73,"size":74,"target":75,"to":76,"trailing-icon":77},"neutral","i-lucide-arrow-right","xl","_blank","https:\u002F\u002Fwww.ll.mit.edu\u002Fnews\u002Fai-models-are-devouring-energy-tools-reduce-consumption-are-here-if-data-centers-will-adopt","i-lucide-external-link","AI's Energy Consumption",[80,81,83],"h2",{"id":82},"two-consequences-of-scaling","Two Consequences of Scaling",[85,86,87],"p",{},"The scaling up of AI models has two major consequences that, together, are reshaping who gets to build with AI.",[89,90,91,101],"card-group",{},[92,93,96,97,100],"card",{"icon":94,"title":95},"i-lucide-zap","More Powerful Models","AI models are becoming ",[63,98,99],{},"more capable of more tasks",", enabling more applications. More people and teams leverage AI to increase productivity, create economic value, and improve quality of life.",[92,102,105,106,109],{"icon":103,"title":104},"i-lucide-cloud","Model as a Service","Training large language models (LLMs) requires data, compute, and specialized talent that ",[63,107,108],{},"only a few organizations can afford",". Those organizations now make their models available for others to use as a service.",[111,112,113],"note",{},"Anyone who wishes to leverage AI to build applications can now use these models without having to invest up front in building one.",[80,115,21],{"id":116},"the-rise-of-ai-engineering",[118,119,120,121,124,125,128,129,132,133,136],"tip",{},"The demand for AI applications has ",[63,122,123],{},"increased"," while the barrier to entry for building them has ",[63,126,127],{},"decreased",". This has turned ",[63,130,131],{},"AI engineering"," — the process of building applications on top of readily available models — into one of the ",[63,134,135],{},"fastest-growing engineering disciplines",".",[80,138,140],{"id":139},"whats-new-whats-not","What's New, What's Not",[85,142,143],{},"Building applications on top of machine learning (ML) models isn't new. Long before LLMs became prominent, AI was already powering many applications.",[89,145,146,150,154],{},[92,147],{"icon":148,"title":149},"i-lucide-shopping-cart","Product Recommendations",[92,151],{"icon":152,"title":153},"i-lucide-shield-alert","Fraud Detection",[92,155],{"icon":156,"title":157},"i-lucide-user-minus","Churn Prediction",[159,160,161,162,165],"warning",{},"While many principles of productionizing AI applications remain the same, the new generation of large-scale, readily available models brings about ",[63,163,164],{},"new possibilities and new challenges"," — the focus of this book.",[80,167,169],{"id":168},"what-this-chapter-covers","What This Chapter Covers",[171,172,174,179,182,186,193,197],"steps",{"level":173},"3",[175,176,178],"h3",{"id":177},"foundation-models","Foundation Models",[85,180,181],{},"An overview of foundation models — the key catalyst behind the explosion of AI engineering.",[175,183,185],{"id":184},"successful-ai-use-cases","Successful AI Use Cases",[85,187,188,189,192],{},"A range of real-world applications, each illustrating what AI is good and ",[63,190,191],{},"not yet good"," at. As AI's capabilities expand daily, predicting its future possibilities becomes increasingly challenging — but existing application patterns can help uncover opportunities today and offer clues about how AI may continue to be used in the future.",[175,194,196],{"id":195},"the-new-ai-stack","The New AI Stack",[85,198,199],{},"What has changed with foundation models, what remains the same, and how the role of an AI engineer today differs from that of a traditional ML engineer.",[111,201,203,204,207],{"icon":202},"i-lucide-info","Throughout this book, ",[63,205,206],{},"traditional ML"," refers to all ML before foundation models.",{"title":57,"searchDepth":209,"depth":209,"links":210},2,[211,212,213,214],{"id":82,"depth":209,"text":83},{"id":116,"depth":209,"text":21},{"id":139,"depth":209,"text":140},{"id":168,"depth":209,"text":169,"children":215},[216,218,219],{"id":177,"depth":217,"text":178},3,{"id":184,"depth":217,"text":185},{"id":195,"depth":217,"text":196},"How the scaling of foundation models reshaped AI, lowered the barrier to building applications, and turned AI engineering into one of the fastest-growing disciplines in software.","md",{},{"icon":19},{"title":11,"description":220},"PtOWhqH5FXmlEtTm7B1_WnOS52KwunTFPPXQNgIKlaw",[6,227],{"title":21,"path":22,"stem":23,"description":228,"icon":24,"children":-1},"Trace how decades of advances in language models, self-supervision, and multimodality produced foundation models — and turned AI engineering into a discipline of its own.",1778484800202]