Article
CommunityJev Media & Talks
Simon Willison: llm-typesafe 0.1a0 plugin for Jev
Simon Willison released llm-typesafe 0.1a0, an LLM plugin for TypeSafe's Jev: install with llm install llm-typesafe, set a typesafe API key, then ask noul yes/no questions, Choice questions and Score questions from the command line. A demo refund question returned noul 0.99.
- Format
- Article
- Reading time
- 2 min
- Published by
- Community
- Author
- Simon Willison
- Last verified
- Oct 2026
Used inJev for Software & DevTools
Highlights
- llm-typesafe 0.1a0 adds TypeSafe AI's Jev model to Simon Willison's LLM command-line tool.
- The demo refund question returned a noul of 0.99, printed as a JSON object with type noul.
- Choice questions pass an answer_type of choice plus a criteria object; the example routes a message to billing, technical or other.
- Score questions pass answer_type of score plus a criteria list; the example rates how reproducible a bug report is.
- The post tells users to set a typesafe API key with llm keys set typesafe and says the waitlist seems to move pretty fast.
Watch out
Copy reviewed against the published release post on 2026-10-17. The piece is a release note by the plugin's own author, it documents the plugin rather than Jev's accuracy, and the only behavioral evidence shown is a single demo question returning a noul of 0.99.
Questions about this entry
Short answers drawn from the linked project or page.
It is a plugin for the LLM command-line tool that adds support for TypeSafe AI's Jev model, released as version 0.1a0 and installed with llm install llm-typesafe.
Set an API key with llm keys set typesafe and paste the key when prompted. The post notes you can get one from TypeSafe and that the waitlist seems to move pretty fast.
You pass the model jev and a statement with -s, such as asking whether a message explicitly requests a refund. Willison's demo returned a JSON object with type noul and a value of 0.99.
Pass -o answer_type choice and a criteria object listing the options, for example billing, technical or other, along with instructions for which to prefer, such as choosing billing when both billing and technical issues occur.
Pass -o answer_type score and a criteria array describing the scale, such as no reproduction instructions, some instructions with missing steps, or complete steps with expected and actual results.
The post points to the README for more details on the plugin. The examples show piping a file into llm with cat and passing the question with -s.
The examples show Jev returning typed answers such as a noul probability of 0.99 rather than generated text, which the plugin exposes through LLM's command-line options for answer_type and criteria.
Reactions & coverage
Posts, threads, and videos about this entry from around the web.
Hacker News: Simon Willison's overview of Noul, Choice, and Score, and where a decision model fits.
benwerd53 pointsJev introduces a new shape of LLMRead the thread on Hacker NewsHacker News: swyx posts the Latent Space interview with Diogo Almeida.
swyx4 pointsJev: System One Models for Prod, Not God – With Diogo Almeida, CEO, TypeSafe AIRead the thread on Hacker NewsX: Diogo Almeida in five minutes
X: LLMs vs. Jev, clearly explained
More Jev resources like this
SiliconANGLE reports TypeSafe closed $870M at a $7.5B valuation and explains the model's pitch: three request types, yes/no answers, picking from a list, or a score, return structured output and a confidence number instead of text.
Jev Media & TalksArticle#community#press#funding
Community
The Economic Times profiles Diogo Almeida, who left OpenAI in 2024 and spent about two years developing the idea behind TypeSafe AI. It cites WSJ on the roughly 25% Fortune 500 adoption and a $40 million DCVC raise.
Jev Media & TalksArticle#community#press#explainer
Community
Same-day reaction to Jev from four engineers: Mario Zechner called it basically a general purpose classifier, Thorsten Ball praised the onboarding, Malte Ubl said it reached AI Gateway, and Armin Ronacher expects fast followers. Wes Bos measured $0.000232 a call and there were no evals yet.
Jev Media & TalksArticle#community#press#adoption
Community
DigitalToday's Korea report relays The Information's September 24 story: TypesafeAI is seeking $1 billion, with some unnamed investors proposing valuations above $10 billion, while the talks remain early and terms could change.
Jev Media & TalksArticle#community#press#funding
Community
INXEN's syndication of Financial Times reporting says TypeSafe, last valued at $200 million, is fielding offers that would value it at $10 billion or more days after launching Jev, with Vercel citing record paid-developer interest.
Jev Media & TalksArticle#community#press#funding
Community
Langfuse's September 18 post presents Jev as a decision model for routing, classification and eval verdicts, and walks through scoring production traces with Jev-as-a-judge in Langfuse.
Jev Media & TalksArticle#community#press#explainer
Community
From the Jev guides
Original write-ups on what this entry is for.
From the Jev AI model community
Posts from builders shipping with Jev right now.