151–160 of 173 posts
The AST approach should be integrated into code generation. Instead of generating text, generate AST nodes. Something like “Copilot with Intellisense” could be a game changer.
You’re going to want to define the acronym RAG before you use it a dozen times in your marketing copy. Presumably it’s great news that I can RAG on my codebase. But I’m not sure whether I’ve ever ragged anything in my career or whether I’ll want to now. If you told us what it meant, we could probably understand what your thing does.
Thanks Jason, you're right. We spend so much time around RAG that we forget this is niche term. RAG -> retrieval augmented generation. Given a query, finding the parts of the codebase most relevant to the query, and supplying it to the LLM so it can answer the query. The typical way to do this is semantic similarity, or chunking + embedding the corpus being searched, embedding the query and finding the k most cosine-…
You’ll want to find a balance between telling people what your thing does with no jargon or acronyms whatsoever, while signaling to people who know as much as you about this stuff (all four of them) that it’s got those cool ingredients.
All the best.
Earlier quoted context omitted.
Thanks Jason, you're right. We spend so much time around RAG that we forget this is niche term. RAG -> retrieval augmented generation. Given a query, finding the parts of the codebase most relevant to the query, and supplying it to the LLM so it can answer the query. The typical way to do this is semantic similarity, or chunking + embedding the corpus being searched, embedding the query and finding the k most cosine-…
Thanks. Even that is pretty dense for someone who hasn’t been living and breathing LLMs for the last year. https://xkcd.com/2501/ You’ll want to find a balance between telling people what your thing does with no jargon or acronyms whatsoever, while signaling to people who know as much as you about this stuff (all four of them) that it’s got those cool ingredients. All the best.
Ran it on a "real" OSS project of mine ( https://github.com/dvx/lofi/ ), and it was stuck at 99% loading for about 30 minutes. Then, when it finally parsed the codebase, when asked anything it always returns "Error: Internal error while locating sources." Specifically, I wanted to see if it can context switch between TypeScript (used for the front-end), ObjectiveC (used for a few Mac features), C++ (used for Windows…
Thanks for reporting the errors. You're right that it's far from perfect. I will say that part of this is due to higher than expected traffic today. We're working hard on stability in general, so hopefully next time you use it you will have a smoother experience.
Earlier quoted context omitted.
Thanks for reporting the errors. You're right that it's far from perfect. I will say that part of this is due to higher than expected traffic today. We're working hard on stability in general, so hopefully next time you use it you will have a smoother experience.
Loved the idea behind the product, @dakshgupta. Hiccups do happen, don't worry much about them. Keep iterating!
I had scrolled past this article without clicking and had the same thoughts about how I'd approach this.
Apparently I’m the only one here who doesn’t know this but: What is RAG?
My first thought for RAG is "Red, Amber, Green" as used on risks etc. with project management.