701–710 of 1001 posts
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.
Earlier quoted context omitted.
> 225 coding exercises from Exercism Has there been any effort taken to reduce data leakage of this test set? Sounds like these exercises were available on the internet pre-2023, so they'll probably be included in the training data for any modern model, no?
I try not to let perfect be the enemy of good. All benchmarks have limitations. The Exercism problems have proven to be very effective at measuring an LLM's ability to modify existing code. I receive a lot of feedback that the aider benchmarks correlate strongly with people's "vibes" on model coding skill. I agree. The scores have felt quite aligned with my hands-on experience coding with most of the top models over…
Very good, Code is extremely nice but as others have said, if you let it go on its own it burns through your money pretty fast. I've made it build a web scraper from scratch, figuring out the "API" of a website using a project from github in another language to get some hints, and while in the end everything was working, I've seen 100k+ tokens being sent too frequently for apparently simple requests, something feels…
It probably makes sense to continue using third party tools such as aider, for now. Anthropic doesn't have a lot of incentives to reduce token usage.
You can get your HN profile analyzed by it and it's pretty funny :) https://hn-wrapped.kadoa.com/ I'm using this to test the humor of new models.
Oh man, I feel seen :)
Earlier quoted context omitted.
My guess is that, yes, the software development job market is being massively disrupted, but there are things you can do to come out on top: * Learn more of the entire stack, especially the backend, and devops. * Embrace the increased productivity on offer to ship more products, solo projects, etc * Be highly selective as far as possible in how you spend your productive time: being uber-effective can mean thinking an…
Do you have any specific tips for the last point? I completely agree with it and have set up a fairly robust Obsidian note taking structure that will benefit greatly from an agentic assistant. Do you use specific tools or workframe for this?
Earlier quoted context omitted.
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),…
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.
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.
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.
How do you feel about raking in millions while attempting to make us all unemployed?
How do you feel about stealing open source code and stripping the copyright?
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.
I'm somewhat impressed from the very first interaction I had with Claude 3.7 Sonnet. I prompted it to find a problem in my codebase where a CloudFlare pages function would return 500 + nonsensical error and an empty response in prod. Tried to figure this out all Friday. It was super annoying to fix as there's no way to add more logging or have any visibility to the issue as the script died before outputting anything.…
One thing about the reply gives away why Claude is still basically clueless about Actual Thinking; it suggested me to move the HTML sanitization to the frontend. It's in the CF function because it would be trivial to bypass it in the frontend making it easy to post literally anything in the db. Even a junior developer would understand this.
It could have done a better job outlining how to do it properly
I'm about 50kloc into a project making a react native app / golang backend for recipes with grocery lists, collaborative editing, household sharing, so a complex data model and runtime. Purely from the experiment of "what's it like to build with AI, no lines of code directly written, just directing the AI." As I go through features, I'm comparing a matrix of Cursor, Cline, and Roo, with the various models. While I'm…
"no lines of code directly written, just directing the AI" /skeptical face. Without fail, every. single. person. I've met who says that, actually means "except for the code that I write", or "except for how I link the code it build together by hand". If you are 50kloc in to a large complex project that you have literally written none of, and have, eg. used cursor to generate the code without any assistance... well, y…