Join 📚 Josh Beckman's Highlights
A batch of the best highlights from what Josh's read, .
RAG is often implemented using [vector search against embeddings](https://simonwillison.net/2023/Oct/23/embeddings/#answering-questions-with-retrieval-augmented-generation), but there’s an alternative approach where you turn the user’s question into some full-text search queries, run those against a traditional search engine, then feed the results back into an LLM and ask it to use them to answer the question.
Building search-based RAG using Claude, Datasette and Val Town
Simon Willison
That's the fundamental problem with self-documenting negative information. "Self-documentation" rides along with written code, and so describes what the code is doing. Negative information is about what the code is *not* doing.
Why not "why not" comments? Not why "not comments"
Computer Things
Goals are about the results you want to achieve. Systems are about the processes that lead to those results.
An Easy & Proven Way to Build Good Habits & Break Bad Ones
James Clear
...catch up on these, and many more highlights
Readwise