Thread

1. tgluck · 1790683599 · focus · HN ↗

   Author here. This puts a proxy in front of repeated Jev classification calls. At first everything goes to Jev; from Jev's answers it trains a small head on frozen sentence embeddings, picks a confidence threshold with an exact finite-sample bound so that at most 2% of all requests get an answer Jev wouldn't have given, and then answers the confident share locally at ~15 ms on a CPU. A permanent 2% audit keeps checking; if agreement breaks, everything falls back to Jev and it retrains.

   Known limits: agreement is not accuracy (if Jev is wrong, so is the local model); coverage tracks how consistent Jev itself is (22% on noisy tweet tasks, 80% on news); it speaks Jev's API only, an OpenAI-compatible front is on the roadmap. Since 0.4.0 the guarantee can also cover "would Jev have been unsure", which matters if your code routes low-confidence answers to review. Apache 2.0.

   1. kodefreeze · 1790701339 · focus · HN ↗

      Isn't this against their ToS? Useful for hobby stuff.

      1. tgluck · 1790708538 · focus · HN ↗

         [dead]

      2. KetoManx64 · 1791003457 · focus · HN ↗

         Why would it be against the rules to use the previous answers that the AI model gave you within your own project? That's like saying you can't use your Claude code convo history to answer questions within your codebase.

Unofficial Hacker News client; not affiliated with Y Combinator.