The Shift from Models to Compound AI Systems – The Berkeley Artificial Intelligence Research Blog
bair.berkeley.edu · 2,691 words · saved by 1 readers
The BAIR Blog
AI caught everyone’s attention in 2023 with Large Language Models (LLMs) that can be instructed to perform general tasks, such as translation or coding, just by prompting. This naturally led to an intense focus on models as the primary ingredient in AI application development, with everyone wondering what capabilities new LLMs will bring. As more developers begin to build using LLMs, however, we believe that this focus is rapidly changing: state-of-the-art AI results are increasingly obtained by compound systems with multiple components, not just monolithic models . For example, Google’s Alpha
related reading
- Building Effective AI Agents \ Anthropicanthropic.com
- As Rocks May Think | Eric Jangevjang.com
- Building Effective AI Agents \ Anthropicanthropic.com
- GenAI Handbookgenai-handbook.github.io
- Patterns for Building LLM-based Systems & Productseugeneyan.com
- Composer2.pdfcursor.com
- LLMs as Parts of Systems - Marc's Blogbrooker.co.za
- AI Horseless Carriages | koomen.devkoomen.dev
- LLM Powered Autonomous Agents | Lil'Loglilianweng.github.io
- What We’ve Learned From A Year of Building with LLMs – Applied LLMsapplied-llms.org
- AI in 2025: gestalt — LessWronglesswrong.com
- My picture of the present in AI — LessWronglesswrong.com