Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Launch HN: Relace (YC W23) – Models for fast and reliable codegen

news.ycombinator.com

Post reply on HN
Print view View original

51–54 of 54 posts

Re: Launch HN: Relace (YC W23) – Models for fast and reliable codegen

#51

Post by mousetree »

This looks great - congrats. Would I be able to build an internal "Chat with your code" type product? I'm looking at the "code reranker" api docs and they require a list of files including the code itself. This would probably be infeasible to send all our code just to get relevancy. Are there any local ways of reducing the list of files and code we send?

We're using Github Copilot chat (the interface hosted at https://github.com/copilot) for this purpose today but I'm curious how one would build such a thing ourselves.

Re: Launch HN: Relace (YC W23) – Models for fast and reliable codegen

#52

Post by cocoflunchy »

ankit219 wrote: post #28
bcyn wrote: post #27

Very interested to see what the next steps are to evolve the "retrieval" model - I strongly believe that this is where we'll see the next stepwise improvement in coding models. Just thinking about how a human engineer approaches a problem. You don't just ingest entire relevant source files into your head's "context" -- well, maybe if your code is broken into very granular files, but often files contain a lot of irrel…

I have a different pov on retrieval. It's a hard problem to solve in a generalizable format with embeddings. I believe this can be solved at a model level where its used to fix an issue. With the model providers (oai, anthropic) going full stack, there is a possibility they solve it at reinforcement learning level. Eg: when you teach a model to solve issues in a codebase, the first step is literally getting the right…

Relevant interview extract from the Claude Code team: https://x.com/pashmerepat/status/1926717705660375463

> Boris from the Claude Code team explains why they ditched RAG for agentic discovery. > "It outperformed everything. By a lot"

Re: Launch HN: Relace (YC W23) – Models for fast and reliable codegen

#53

Post by willchen »

I tried sending an email to support@relace.ai (which was linked in the doc) and got:

Your message wasn't delivered to support@relace.ai because the address couldn't be found, or is unable to receive mail.

btw, I'm interested in trying out relace for my AI app generator tool: http://dyad.sh/

Re: Launch HN: Relace (YC W23) – Models for fast and reliable codegen

#54

Post by ankit219 »

cocoflunchy wrote: post #52
ankit219 wrote: post #28

Earlier quoted context omitted.

I have a different pov on retrieval. It's a hard problem to solve in a generalizable format with embeddings. I believe this can be solved at a model level where its used to fix an issue. With the model providers (oai, anthropic) going full stack, there is a possibility they solve it at reinforcement learning level. Eg: when you teach a model to solve issues in a codebase, the first step is literally getting the right…

Relevant interview extract from the Claude Code team: https://x.com/pashmerepat/status/1926717705660375463 > Boris from the Claude Code team explains why they ditched RAG for agentic discovery. > "It outperformed everything. By a lot"

This is very cool. They explained the solution better than I did. If I knew, I would have just linked this :)
Post reply on HN