Field notes from Jevathon: Jev returns typed decisions, not prose
schwentker · x · 2026-09-27
The author shares field notes from Jevathon, a hackathon in SF hosted by CodeRabbit with Typesafe AI and AI Collective.
- Jev is a Typesafe AI model whose key trait is returning typed decisions rather than natural-language text.
- Demo projects ranged widely: a wolf simulation, dog sculptures, stroke triage, and a GitHub roast bot — all using Jev as the judgment layer.
- This is part 1 of a six-post series; later parts cover pricing, usage patterns, and the roadmap.
More from coding & agent
- Dev: We'll soon forget how bad hand-written code used to be — facontidavide · 2026-09-27
- A Classical Operating Manual for Spotting Bad-Faith Arguments in Public Forums — Promptmethus · 2026-09-27
- CS grad spent 3 days writing a parser that Claude could build in 20 seconds — deepakns · 2026-09-27
- Creator spends $3,000 remaking 301 viral video effects with Claude Opus 5.5, open-sources all prompts — yihui_indie · 2026-09-27
- 282 viral Claude Opus 5.5 videos with exact prompts open-sourced on GitHub — yihui_indie · 2026-09-27
- Who is building an agent-first programming language optimized for correctness, not humans? — burny_tech · 2026-09-27