How Jev eases the runtime intelligence cost tension
Small decisions like classify, route and score go to Jev, trading runtime dynamic intelligence for a cost close to compile-time code.
Congrats @typesafeai !! What's so cool about Jev is that it breaks the tension between expensive, dynamic intelligence at runtime (w/ opex costs) and cheap, brittle intelligence at compile time (w/ capex costs). More: - One tension between labs and their customers is the economics of coding agents vs general agents w skills / projects / memory - We went from fat apps (most of 2025) to thin apps that mostly wrap intelligence, with code as a disposable artifact generated at runtime - Generating code is a crystallization of inference. It captures business logic that could otherwise live in the model as static procedural logic. Cheap to run, but brittle - The alternative is regenerating everything dynamically at runtime with PhD-level models w reasoning, memory, tools. More elegant / general, but the most token consumptive: you pay opex every time you use the app vs capex once - This partially explains why labs have pushed so hard for skills / projects / agents over code first - the general agent approach drives far more token consumption - Most runtime "intelligence" is small decisions: classify / route / score / pick. A fast, cheap System One model gives you dynamic intelligence at runtime for roughly the cost of compile-time code - So the future stack should be code generated by models at compile time, Jev-style decisions at runtime, and frontier agents + tools reserved for genuinely open-ended work I LOVE this model & I'm very excited to see what comes next.
This post quotes another post: x.com/jenniferhli/status/2108596399365640520