Viewing profile — danmeier

Everyone is talking about token spend, but not what we actually spend tokens on. I’ve always found it interesting to track my time across different tasks to challenge whether I was…

Great semantic diffs, but does Lix actually define a merge algebra for concurrent structured edits, or are conflicts just punted back to humans? How does its SQL engine guarantee d…

Hot take: I think all these dictation tools are solving the wrong problem: they're optimizing for accurate transcription (and latency) when users actually need intelligent interpre…

very interesting! curious to see the benchmarks for MCP!

Why are you not just using the chunkers from unstructured ?

Hey HN We've just released the initial version of our open-source vector embedding pipeline. It's designed to embed large volumes of data. While embedding a few documents for Q&A i…