Useful LLM fit tool
Brett Dargan
Tech Co-Founder | Architect | Strategist
Blog
Web local LLM apps
Brett Dargan
Tech Co-Founder | Architect | Strategist
Will be interesting to see how this tech evolves: Privacy First: Building LLM-Powered Web Apps with client side WASM by Shivay Lamba & Saiyam Pathak - YouTube
OpenAI and Meta E9 = The Career Bet Ever Engineer Must Make
Brett Dargan
Tech Co-Founder | Architect | Strategist
Engineering decisions
OpenAI and Meta E9: The Career Bet Every Engineer Must Make - YouTube
Interesting to hear Plumbing and HVAC got mentioned in the first few minutes and stories of Plumbers making there own customer scheduler from AI.
2026 Week 07 - Deno sandboxes
Brett Dargan
Tech Co-Founder | Architect | Strategist
2026W07
Q: Have an untrusted code from your LLM?
Deno sandboxes might do the trick, or atleast show you how to.
2026 Week 06 - Search and mixture of models
Brett Dargan
Tech Co-Founder | Architect | Strategist
2026W06
Trying out Opencode with direct xAI provider.
Interesting paper on search / retrieval
Superlink bm25 and mixture of models.
GitHub - parthsarthi03/raptor: The official implementation of RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval Airbnb Search Benchmarking - Comparison of retrieval techniques | VectorHub by Superlinked
Way back we used Elasticsearch for hotel search at Wotif.com, interesting this approach with mixing of models.
- read later: Sign-rank theory
- Hadamard matrix
On Local-First
Watched an intewview with jamsocket creator in my local-first readings, plane is super interesting.
RAG from scratch
- Been on the backlog for ages to use build a RAG over my notes - time to pick one of these paths and just get it done.
- Code a simple RAG from scratch
- A beginner’s guide to building a Retrieval Augmented Generation (RAG) application from scratch
- Local Retrieval Augmented Generation (RAG) from Scratch (step by step tutorial) - YouTube
- https://superlinked.com/vectorhub/articles/fix-search-as-pm