Labs, prototypes and unfinished tests. Useful even when they fail.
Experiments is for labs, prototypes and unfinished tests. A failed run still belongs here if the method or the measurement is useful. Setup and numbers come before a conclusion.
Titles, summaries and this definition are in the HTML. JavaScript only opens the mobile menu.
Jev is a newly released decision model from TypeSafeAI. I test whether its combination of seconds-scale classification, very low inference cost and usable semantic accuracy can make large-scale chat-history analysis practical.
A company rarely has one document to connect to an AI system. It has hundreds of policies, contracts, scanned PDFs, technical reports, presentations, tables and Excel workbooks. From the outside, the task looks straightforward: upload the file, extract the text, split it into chunks and send it to a vector database.