←back to thread

Claude 3.7 Sonnet and Claude Code

(www.anthropic.com)
2127 points bakugo | 5 comments | 24 Feb 25 18:28 UTC | HN request time: 0s | source
Show context
bcherny ◴[24 Feb 25 19:04 UTC] No.43163488[source]▶
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.
replies(82): >>43163527 #>>43163532 #>>43163549 #>>43163554 #>>43163555 #>>43163576 #>>43163585 #>>43163588 #>>43163589 #>>43163592 #>>43163593 #>>43163632 #>>43163642 #>>43163664 #>>43163677 #>>43163733 #>>43163758 #>>43163789 #>>43163803 #>>43163813 #>>43163821 #>>43163893 #>>43163909 #>>43163915 #>>43163921 #>>43163957 #>>43163958 #>>43163992 #>>43164069 #>>43164089 #>>43164102 #>>43164103 #>>43164104 #>>43164111 #>>43164127 #>>43164158 #>>43164329 #>>43164353 #>>43164424 #>>43164482 #>>43164514 #>>43164585 #>>43164616 #>>43164768 #>>43164797 #>>43164819 #>>43164899 #>>43165002 #>>43165057 #>>43165065 #>>43165088 #>>43165091 #>>43165187 #>>43165308 #>>43165355 #>>43165409 #>>43165468 #>>43165499 #>>43165516 #>>43165570 #>>43165578 #>>43165592 #>>43165836 #>>43165884 #>>43165965 #>>43165976 #>>43165995 #>>43166183 #>>43166711 #>>43166748 #>>43167130 #>>43167804 #>>43168626 #>>43168836 #>>43169047 #>>43169107 #>>43169119 #>>43169294 #>>43169310 #>>43173097 #>>43174353 #>>43192161 #
antirez ◴[24 Feb 25 19:50 UTC] No.43164089[source]▶
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.
replies(1): >>43164253 #
bcherny ◴[24 Feb 25 20:03 UTC] No.43164253[source]▶
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.
replies(1): >>43164503 #
marlott ◴[24 Feb 25 20:23 UTC] No.43164503[source]▶
Interesting - can you elaborate a little on what you mean by agentic search here?
replies(2): >>43164993 #>>43166130 #
simonw ◴[24 Feb 25 23:20 UTC] No.43166130[source]▶
Since the Claude Code docs suggest installing Ripgrep, my guess is that they mean that Claude Code often runs searches to find snippets to improve in the context.

I would argue that this is still RAG. There's a common misconception (or at least I think it's a misconception) that RAG only counts if you used vector search - I like to expand the definition of RAG to include non-vector search (like Ripgrep in this case), or any other technique where you use Retrieval techniques to Augment the Generation phase.

IR (Information Retrieval) has been around for many decades before vector search become fashionable: https://en.wikipedia.org/wiki/Information_retrieval

replies(2): >>43168083 #>>43168903 #
jcheng ◴[25 Feb 25 06:39 UTC] No.43168903[source]▶
I agree that retrieval can take many forms besides vector search, but do we really want to call it RAG if the model is directing the search using a tool call? That like an important distinction to me and the name "agentic search" makes a lot more sense IMHO.
replies(1): >>43169099 #
1. simonw ◴[25 Feb 25 07:12 UTC] No.43169099[source]▶
Yes, I think that's RAG. It's Retrieval Augmented Generation - you're retrieving content to augment the generation.

Who cares if you used vector search for the retrieval?

The best vector retrieval implementations are already switching to a hybrid between vector and FTS, because it turns out BM25 etc is still a better algorithm for a lot of use-cases.

"Agentic search" makes much less sense to me because the term "agentic" is so incredibly vague.

replies(1): >>43169580 #
2. regularfry ◴[25 Feb 25 08:45 UTC] No.43169580[source]▶
I think it depends who "you" is. In classic RAG the search mechanism is preordained, the search is done up front and the results handed to the model pre-baked. I'd interpret "agentic search" as anything where the model has potentially a collection of search tools that it can decide how to use best for a given query, so the search algorithm, the query, and the number of searches are all under its own control.
replies(2): >>43174140 #>>43183513 #
3. jcheng ◴[25 Feb 25 16:40 UTC] No.43174140[source]▶
Exactly. Was the extra information pushed to the model as part of the query? It’s RAG. Did the model pull the extra information in via a tool call? Agentic search.
replies(1): >>43186485 #
4. simonw ◴[26 Feb 25 13:39 UTC] No.43183513[source]▶
This is a really useful definition of "agentic search", thanks.
5. regularfry ◴[26 Feb 25 18:24 UTC] No.43186485{3}[source]▶
That's far clearer. Yes.