OrcaRouter on what Jev needs as a System 1 decision model
OrcaRouter argues that most open-source decision models are 27B Qwen3.8-based, and says Jev as a System 1 model should add state awareness, uncertainty recognition, ACT/ABSTAIN/ESCALATE escalation, and action selection.
We’ve been seeing a wave of open-source “decision models” lately, and many of them are 27B because they’re built on the same Qwen3.8 27B foundation. A lot of them open-source weights but don’t host a serious API. There’s a reason: 27B is expensive to keep in the hot path. That brings us back to the fundamentals (Kahneman’s framing): System 1 should be fast, cheap, always-on and action-oriented. System 2 should be slower, deeper and invoked when needed. If your System 1 needs an expensive 27B reasoning model for every decision, you may have just built another smaller System 2. We’re not saying Jev is the final form of a system 1 model. But we think a few capabilities should be added/improved to make it better without increasing the footprint: Statefulness — understand what happened before, what changed, and the current belief state. OOD / uncertainty recognition — know when it doesn’t know. Native escalation — not just output confidence, but choose: ACT / ABSTAIN / ESCALATE. Action selection — move from “answer this question” to: “given the current state, what should happen next?” That’s what we think a real System 1 should optimize for. Not maximum intelligence per call. Maximum useful decisions per dollar, with the judgment to know when to escalate to a System 2!