And it reads to me like they have some other reason to move on from SWE Bench Pro, but they don't want to say what it is. They say right up top, "~30% of the tasks are broken." But that leaves ~70% un-broken, which seems pretty good to me. It would be nice if they would also say: "Here's the list of instances that are broken: <CSV>". Or, "Here's the subset of SWE Bench Pro we will use going forward." They're letting the perfect be the enemy of the good.
Still plugging away on SourceMinder (https://github.com/ebcode/SourceMinder). I know, I know, everyone and their brother is working on token-saving schemes for LLMs. But I’ve found it to be useful even without the LLM. I’m working on a proper website for it now where you can try it out in the browser (wasm port) — try before you don’t buy (it’s GPL). Feedback welcome.
I’m working on a tool that is a more token-efficient code search than grep. I don’t have hard numbers yet, but it’s been working for me to get longer sessions. https://github.com/ebcode/SourceMinder
SourceMinder: A “code index” tool that finds symbols in a codebase and creates a single table sqlite database for the index. It uses tree-sitter to parse the AST and add the symbols and what they are (function, class, argument, etc) to the db. I currently have it working with TypeScript, C, Go and PHP. I’m working on adding Perl next, after someone requested it here on HN.
Yep! Java, Perl, and Ruby are all on the to-do list. I’ll start with Perl since you asked. And it takes me about two weeks to implement a new language. Check back in January.
> A 10% improvement every month gets to be a 10x improvement in (math...)
1.1^24=9.85, so yeah, if you could reliably get a 10% speed-up each month, you’d get to 10x in roughly 2 years. (But I’d expect the speed-up per month to be non-linear.)
I picked these up at a used bookstore ages ago, since they had the three-volume set. My recommendation would be to familiarize yourself with just the table of contents that’s printed on the binding, and when you come across something adjacent in your day-to-day work (e.g. Search), review the papers in that section. Those books are an excellent snapshot of the field at the time.
No, not yet. I'm planning on a proper Show HN, once C and PHP are implemented. But if you want to be updated when I release it, I just created an empty repo for it here: https://github.com/ebcode/indexer-c
A “code index” tool that finds symbols in a codebase and creates a single table sqlite database for querying. It’s my second month using Claude Code, and I see a common pattern where Claude tries to guess patterns with grep, and often comes back with empty results. I’m writing the tool to prevent these fruitless searches. Using tree-sitter to parse the AST and add the symbols and what they are (function, class, argument, etc) to the db. I have it working with TypeScript, and am working on adding C and PHP.
Into open source software, and other forms of freedom.
Feel free to reach out: <username>@proton.me