We previously launched Auto Wiki (https://news.ycombinator.com/item?id=38915999) in Jan 2024 and broke the ground for AI generated wikis that explain your code. Now this product has been rebuilt by the same team, as well as others and launched as a part of Google. Hope you enjoy.
Although, I've recently moved on to working on Gemini and AI research, I'm still involved as an advisor and founder emeritus of sorts. This team moves extremely fast and while we don't have full availability yet, we're working hard on addressing some early feedback before we make it more widely available including for private repos. Personally, I think the NotebookLM integration is a nice touch and distinguishing factor that we could only do as Google.
I hope you enjoy.
Thank You, Omar (Formerly Founder/CEO MutableAI)
We're thrilled to have built a codebase chat that leapfrogs traditional RAG techniques by feeding LLMs a wiki of a codebase to answer questions.We want to take this to the next level, we're doing cutting edge research on MCTS, agents, to take our expert to the next level and be able to autonomously execute tasks on codebases as well as answer any question on a repo.Apply to open roles here:...
https://twitter.com/mutableai/status/1813815706783490055
TL;DR: Vector-based RAG performs poorly for many real-world applications like codebase chats, and you should consider 'language maps'.Part of our mission at Mutable.ai is to make it much easier for developers to build and understand software. One of the natural ways to do this is to create a codebase chat, that answer questions about your repo and help you build features.It might seem simple to...
for it to stay up to date simply have an active subscription and we'll take care of the rest!
https://wiki.mutable.ai/Dao-AILab/flash-attention
Hi HN!We wanted to introduce our codebase chat that uses a wiki of your repo to do retrieval instead of traditional vector or keyword RAG.We have been pleasantly surprised by the quality of responses. We think creating a language knowledge base for LLMs to do RAG is the future. The way this works is we first write a Wikipedia style article on your codebase complete with diagrams and citations...