31–40 of 54 posts
Nice! I am currently writing a new version of my no-code platform, WeBase [1], to use AI to generate and edit applications. Currently just using foundation models from OpenAI and Gemini but will be very interested to try this out. My current approach is to just completely overwrite files with new updated version but I am guessing using something like Relace will make the whole process more efficient... is that correc…
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…
If a file is "relevant" the agent looks at it and decides if it should keep it in context or not. This process repeats until there's satisfactory context to make changes to the codebase.
The question is whether we actually need a 200b+ parameter model to do this or if we can distill the functionality onto a much smaller, more economical model. A lot of people are already choosing to do it with Gemeni (due to the 1m context window), and they write the code with Claude 4 Sonnet.
Ideally, we want to be able to run this process cheaply in parallel to get really fast generations. That's the ultimate goal we're aiming towards
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…
If I understand correctly, the ‘apply’ model takes the original code, an edit snippet, and produces a patch. If the original code has a lot of surrounding context (e.g., let’s say you pass it the entire file rather than trying to assess which bits are relevant in advance), are speed and/or performance materially affected (assuming the input code contains no duplication of the code to be amended)?
Does / how well does any of this generalise to non-code editing? Could I use Relace Apply to create patches for, e.g., plain English markdown documents? If Apply is not a good fit, is anyone aware of something suitable in the plain English space?
What in god’s name does this even mean ?
> For both vibe-coded and enterprise codebases What in god’s name does this even mean ?
This is very interesting. There was also an article and discussion a couple of days ago on using diffusion models for edit/apply tasks at ~2k tps[1]. If I understand correctly, the ‘apply’ model takes the original code, an edit snippet, and produces a patch. If the original code has a lot of surrounding context (e.g., let’s say you pass it the entire file rather than trying to assess which bits are relevant in advanc…
You can definitely use it for markdown, but we haven't seen anyone test it for plaintext yet. I'm sure it would work though, let us know if you end up trying it!