jev.BaseModel: a drop-in Pydantic replacement that coerces state into typed outputs in milliseconds
AAAzzam · x · 2026-09-19
- Developer aaazzam released jev.BaseModel, a drop-in replacement for Pydantic BaseModel built on TypeSafe's System One model Jev, coercing unstructured state into validated, typed outputs in milliseconds — more type-safe and Pythonic than raw Jev.
- How it works: the @jev.fn decorator compiles a Python function signature (params, docstring, return annotation) into a query against Jev. Jev generates no text; it answers typed questions about a state — yes/no probabilities, choices, scores — in one parallel call with calibrated probabilities.
- Design constraint: the return annotation must be a Pydantic model, with each field mapping to one of Jev's three question types. The author's thesis: a function signature is already a complete specification of a decision.
More from coding & agent
- Law professor's five-week method turns students from prompters into AI tool builders — jkubicki · 2026-09-19
- No Prompt, No JSON Parsing: Jev's Typed API Maps Straight onto Java Records — therealdanvega · 2026-09-19
- Non-technical user rebuilds a community bot with Codex in ~20 minutes — Travi3000 · 2026-09-19
- Agent categorizes 63,045 emails in under 3 minutes for less than $1 — NathanWilbanks_ · 2026-09-19
- Edward Yang: LLM-Annotated Terminals Make One-Off Dynamic Analyses Trivial — ezyang · 2026-09-19
- mitsuhiko: team gave web components an honest chance, went all in on React — mitsuhiko · 2026-09-19