Don't classify. Hallucinate!
A useful pattern for LLM classification at scale is to let it hallucinate plausible, fake entities. Then resolve to real ones.
Doug Turnbull
Doug Turnbull's personal blog and essays
Latest posts
Vectors Week: become a savier vector db customer
A week of wector wevents - vector retrieval, hybrid search, combining the dense and lexical.
Just brute force your embeddings
Sure its not fancy, but you might save operational headaches by just brute-forcing vector search for a small enough corpus
Principal Component Analysis: an embedding shrink-ray
Let's walk through basics of using PCA to reduce dimensionality of embeddings
Don't ask what you want. Ask who you want to be
A revelation has occured to me. Don't obsess about what you want. Figure out who you want to be.
Why write code in 2026
A bunch of reasons to write code in 2026
Write code, not specs
In the before times, code was deterministic and self documenting. Why don't we show AI what we want by... just writing some of the code?