Last month I shipped an eval that ranked two prompt variants. Variant A won by four points. A...
An LLM judge is a biased instrument, not a measurement
Related
MythX shut down in March and nothing replaced it so I built something
If you were using MythX before March 31st, you already know. ConsenSys quietly sunset the entire...
A Bank Wanted to Use AI to Approve Loans Faster, Here Is What I Would Build Around It in NestJS
A loan officer at a small digital bank was excited about the new model the data team had built. It...
Croc GUI: Encrypted Peer-to-Peer File Transfer Without the Terminal (Cross-Platform)
TL;DR Croc GUI is a free desktop app for schollz/croc — encrypted peer-to-peer file...