Jev, the first decision-only AI model, makes calls in 200ms for a fraction of a cent
Cole Medin · youtube · 2026-09-21
Cole Medin demos Jev, a new class of AI model that generates no text at all—it takes a state and a list of typed questions and returns probabilistic decisions in 200ms at negligible cost. Use cases he tested include playing his indie game at three decisions per second, triaging every open PR in his repo, and routing each agent request to the right model. His core claim: any gate in your AI coding setup that used to be a regex or a slow LLM call is now a candidate for Jev. Community demos include Jev playing Doom, browser automation via browser-use/jev-ultrafast, Jev vs. LLMs at Pong, and the Awesome Jev collection.
More from coding & agent
- Dev adds a perf monitor to jev: agent watches bottlenecks and flips settings every 5 seconds — tomjohndesign · 2026-09-21
- Google open-sources AX, an agentic orchestrator likened to Kubernetes for agent executions — arpit_bhayani · 2026-09-21
- Watching Claude use a Charuco board to estimate product dimensions from a photo and model it in OpenSCAD — _Stocko_ · 2026-09-21
- AI intern cuts job boot time ~60%, saving ~5 CPU-days per day — DanielLockyer · 2026-09-21
- Anthropic engineer demos 22-minute async Claude Code workflow that runs unattended — anthara_ai · 2026-09-21
- Would coding agents do fine with just bash? Benchmarking without read/write/edit tools — lucasmeijer · 2026-09-21