Jev becomes fastest-adopted AI model ever, spawning sub-cent browser and trading agents in 3 days
multiply_matrix · x · 2026-09-25
TypeSafe's Jev is being called the fastest-adopted model in AI history, with a wave of open-source projects built on it within three days:
- jev-ultrafast: a browser agent with a dynamic, indexed action space — Jev picks operations and elements itself, invoking a small LLM only for TYPETEXT. It found real Zurich→London flight results on Google Flights in 7.1 seconds at $0.0039 per run; 19.9k stars.
- jev-trader: a live trading bot placing limit orders on Monad every 300ms block, judged entirely by Jev.
- jev-usecases: a production security-operations harness where Jev triages incidents with confidence-gated escalations — zero false escalations in the committed test set.
- tax-doc-classifier: 100% strict accuracy across 261 real IRS forms at roughly $0.001 per page.
The companion article "Jev Engineering: The Model That Refuses to Talk" argues the model's deliberate refusal to generate text is the whole point, minimizing generation overhead.
Related event: TypeSafe's Jev Becomes Fastest-Adopted AI Model, Sparking Agent Ecosystem(4 posts)→
More from coding & agent
- DigitalOcean hosts classifier model Jev as a first-class agent tool, not an endpoint — hardimanjames · 2026-09-25
- The wiki is an anti-pattern: docs must live in the repo for coding agents to maintain — TechPreacher · 2026-09-25
- Microsoft Foundry adds voice experiences for AI agents — lee_stott · 2026-09-25
- Caching policy lookups per inode cuts eBPF security agent CPU cost ~90% — JeremyCMorgan · 2026-09-25
- jev-test-impact uses an LLM to pick which tests to run from a Git diff — alchemist-301 · 2026-09-25
- Astronomer builds his dream learning tool in ~5 hours with Opus 5.5, now live — niloofar_mire · 2026-09-25