Claude 3.7 Sonnet and Claude Code

Hi everyone! Boris from the Claude Code team here. @eschluntz, @catherinewu, @wolffiex, @bdr and I will be around for the next hour or so and we'll do our best to answer your questions about the product.

One of the silver bullets of Claude, in the context of coding, is that it does NOT use RAG when you use it via the web interface. Sure, you burn your tokens but the model sees everything and this let it reply in a much better way. Is Claude Code doing the same and just doing document-level RAG, so that if a document is relevant and if it fits, all the document will be put inside the context window? I really hope so! Also, this means that splitting large code bases into manageable file sizes will make more and more sense. Another Q: is the context size of Sonnet 3.7 the same of 3.5? Btw Thanks you so much for Claude Sonnet, in the latest months it changed the way I work and I'm able to do a lot more, now.

Right -- Claude Code doesn't use RAG currently. In our testing we found that agentic search out-performed RAG for the kinds of things people use Code for.

Interesting - can you elaborate a little on what you mean by agentic search here?

I guess it's what sometimes it's called "self RAG", that is, the agent looks inside the files how a human would be to find that's relevant.

As opposed to vector search, or…?

To my knowledge these are the options:

1. RAG: A simple model looks at the question, pulls up some associated data into the context and hopes that it helps.

2. Self-RAG: The model "intentionally"/agentically triggers a lookup for some topic. This can be via a traditional RAG or just string search, ie. grep.

3. Full Context: Just jam everything in the context window. The model uses its attention mechanism to pick out the parts it needs. Best but most expensive of the three, especially with repeated queries.

Aider uses kind of a hybrid of 2 and 3: you specify files that go in the context, but Aider also uses Tree-Sitter to get a map of the entire codebase, ie. function headers, class definitions etc., that is provided in full. On that basis, the model can then request additional files to be added to the context.

I'm still not sure I get the difference between 1 and 2. What is "pulls up some associated data into the context" vs ""intentionally"/agentically triggers a lookup for some topic"?