Building LLM applications for production

[Hacker News discussion, LinkedIn discussion, Twitter thread]

[ Hacker News discussion , LinkedIn discussion , Twitter thread ] Update: My upcoming book, AI Engineering (late 2024/early 2025) will cover building aplications with foundation models in depth. A question that I’ve been asked a lot recently is how large language models (LLMs) will change machine learning workflows. After working with several companies who are working with LLM applications and personally going down a rabbit hole building my applications, I realized two things: It’s easy to make something cool with LLMs, but very hard to make something production-ready with them. LLM limitation

related reading

• Patterns for Building LLM-based Systems & Productseugeneyan.com
• LLM Powered Autonomous Agents | Lil'Loglilianweng.github.io
• What We Learned from a Year of Building with LLMs (Part I) – O’Reillyoreilly.com
• What We’ve Learned From A Year of Building with LLMs – Applied LLMsapplied-llms.org
• The architecture of today's LLM applications - The GitHub Bloggithub.blog
• What We Learned from a Year of Building with LLMs (Part II) – O’Reillyoreilly.com
• GenAI Handbookgenai-handbook.github.io
• The Foundation Understanding LLMs and Prompt Engineering, and Why It All Mattersleeboonstra.dev
• LLM Evaluation doesn't need to be complicatedphilschmid.de
• Model optimization | OpenAI APIplatform.openai.com
• Building Effective AI Agents \ Anthropicanthropic.com
• Evaluating LLM Applicationshumanloop.com