oshams

↗ HN profile [ 73.8 ms ] full profile

No user record in our sample, but oshams has activity below (stories or comments). Likely we have partial data — the full bulk-load will fill profiles in.

  1. 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…

  2. 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…

  3. 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…

  4. Hi HN! I'm Omar from Mutable.ai. We previously (https://news.ycombinator.com/item?id=38915999) introduced Auto Wiki (http://wiki.mutable.ai/)), which transforms your codebase into Wiki-style articles with citations to…

  5. Hi HN! I’m Omar from Mutable.ai. We want to introduce Auto Wiki (https://wiki.mutable.ai/), which lets you generate a Wiki-style website to document your codebase. Citations link to code, with clickable references to…

  6. Hi HN! We’re MutableAI (YC W22) (https://mutable.ai). Our mission is to reduce the time and cost to create high quality code using AI. We have worked at the full gamut of companies ranging from startups to big tech and…

  7. Hi HN, I’m Omar the Founder and CEO of MutableAI (YC W22) (https://mutable.ai). We transform Jupyter notebook code into production-quality Python code using a combination of AI (OpenAI codex) and PL metaprogramming…