llm-typesafe 0.1a0
- ID
- 27293
- Status
- summarized
- Published
- 22 Sep 2026, 11:54 PM
- Fetched
- 23 Sep 2026, 12:47 AM
- Provider
- Simon Willison
- Category
- developer-ai
- Original URL
- https://simonwillison.net/2026/Sep/22/llm-typesafe/
- Source URL
- https://simonwillison.net/atom/everything/
Summary
- Score
- 7.0
- Created
- 23 Sep 2026, 12:47 AM
- Tags
- Audience
- developersai_ml_learnersai_agent_users
What happened
Simon Willison released llm-typesafe 0.1a0, a plugin for his `llm` CLI tool that adds support for TypeSafe AI's Jev model — a 'Decision Model' that outputs structured yes/no ('noul'), choice, or score answers instead of free-form text. You install it with `llm install llm-typesafe`, set an API key via `llm keys set typesafe`, and can then pipe text into Jev for classification, routing, or scoring tasks with JSON output.
Why it matters
If you build agent routing, message triage, or content classification pipelines, Jev's structured output modes (noul, choice, score) could replace fragile prompt-and-parse patterns with a model designed specifically for decisions. Worth testing against your current approach to see if decision models are more reliable or cheaper than prompting a generative model and extracting structured output.
Discussion angle
Compare Jev's decision-model paradigm against the common pattern of using a generative LLM with JSON mode for classification — is a purpose-built decision model actually more reliable, or is this just a constrained wrapper around the same underlying capability?