RVRC's comments

On: Show HN: Code Claude Code

[RVRC]

I haven’t used Gemini as much but it doesn’t seem as smart as Claude, especially at exploring the codebase.

I’ve never heard of prompt tower either, so definitely something to look into!

On: Show HN: Code Claude Code

[RVRC]

Very true!

This isn’t the product I’m building which is why i opened sourced it, but it allows for my product to be made

I’m sure Anthropic will release this exact sdk in a week or two

On: Show HN: Code Claude Code

[RVRC]

Paul!!!

I first made a scripting tool of aider that I didn't open source: (https://cloudcoding.ai)

Scripting with aider gives lower level control but this is also its shortcoming to why I prefer scripting Claude code.

Claude code is like a better architect mode and people want higher and higher levels of abstraction away from the coding and more towards the vibing.

On: Launch HN: Continue (YC S23) – Create custom AI code assistants

[RVRC]

TLDR: Is there a way to make money from creating these specialized agents?

[sestinj → RVRC]

Nothing built-in yet, but if you have a service that lets users pay for API keys then you can achieve this in effect. There are already some good examples:

- Models like Relace's Instant Apply (https://hub.continue.dev/relace/instant-apply)

- Codebase context services like Greptile (https://hub.continue.dev/continuedev/greptile-context)

- MCP servers for services like Exa (https://hub.continue.dev/exa/exa-mcp)

On: Ask HN: What have you built with LLMs?

[RVRC]

I’m also building a RAG app and I’m finding so many different ways to do it.

I’m curious: was there one method that improved the accuracy/relevance of the answers the most?

Also, are you using Langchain, Llamaindex, or something else?

[sturza → RVRC]

used langchain but for this implementation i used llamaindex. bsturza@duck.com