Small decisions. Interesting possibilities.Submit a project / videoSubmit
Experiments

Jevcal confidence-threshold calibration

Everyone picks Jev confidence thresholds by vibes. 0.95? 0.5? I built jevcal. Give it your data and say "I need 99% accuracy". You get the exact threshold, how much Jev can handle, and how much still needs an LLM. Open source, one command. @typesafeai

X post ↗GitHub ↗

How it uses Jev

Uses Jev to make the bounded decisions demonstrated by Jevcal confidence-threshold calibration.

Why it's interesting

Shows a concrete Jev-driven result in public media and passed the verified engagement threshold.

How often does Jev run?

This project calls Jev on demand, in response to user input or events.

  • jevchat

    Turns Jev into a chatbot

  • Breaking, golden nugget, or slop

    Jev is tagging X posts in real time for me. Breaking, golden nugget, or slop.

  • Which exam questions come back

    JEV IS INSANE. I gave it 80 real exam questions and 297 practice ones. In 80 seconds, it told me which ones are most likely to appear on the real exam and which ones aren’t. All for $0.0256. Can't stop playing with @typesafeai 😁

Explore more in Experiments →