Tag
An article discussing which AI model is best suited for generating technical documentation.
A blog post reflecting on the surge of LLM-assisted hobby projects, questioning their real-world utility and urging creators to consider the purpose beyond the initial dopamine rush.
Kapa.ai describes their approach to indexing images for RAG by using a cheap vision model to generate text descriptions at indexing time, avoiding query-time vision costs, resulting in better answers with minimal per-query overhead.