Blog
Benchmarks, design decisions and how-tos: building AI agents in Synsema, and deploying them with a permission manifest, sealed secrets and an audit trail. Every post is also Markdown: add .md to its URL.
6 results for system-one
The judge slot is a protocol, not a vendor. Since v0.6.27 a Laya checkpoint on disk — ModernBERT, Apache 2.0 — answers whether, choose and rate with no network, no secret and no cost per token, and the same block runs unchanged.
The calibrated probability that decides what a person sees no longer has to come from an API. An open-source System One checkpoint on your own disk answers the same typed questions with no key, no network and no cost per token — and the same program runs against either one.
Routing, tagging, eligibility and moderation are the highest-volume AI work most products do, and the cheapest to get wrong. A System One model answers them with a calibrated probability — and the economics are not close.
Half the work we hand to an LLM is not writing, it is deciding: route this, flag that, is this a refund request. A System One model answers those with a calibrated distribution, and a language that has both slots lets each model do the half it is good at.
A model that returns calibrated probabilities instead of text changes the operational questions, not just the code. What to wire, what to gate, what to audit, and what happens on the day the provider is down.
Jev is TypeSafe's System One model: it answers with typed, calibrated probabilities instead of text. In Synsema it is a language primitive — `require judge`, one block, one call, three verbs — with honest degradation when it is not there.