llm-typesafe 0.1a0
Simon Willison released llm-typesafe 0.1a0, a plugin for TypeSafe AI's Jev model.
Simon Willison released llm-typesafe 0.1a0, a plugin for his LLM command-line tool that calls TypeSafe AI's Jev model. After installation and an API key, users can ask yes/no noul questions or constrained choice questions. A sample noul response is JSON such as {"type":"noul","noul":0.99}. The release is an early alpha plugin rather than a new foundation model.
- llm-typesafe 0.1a0 is a plugin for the LLM CLI.
- It adds access to TypeSafe AI's Jev model.
- Supports noul yes/no scores and constrained choice answers.
- Users install it with llm and set a TypeSafe API key.
Release: llm-typesafe 0.1a0 I built this new plugin for LLM to add support for TypeSafe AI's new Jev model . Install it like this: llm install llm-typesafe Then set an API key ( get one here , the waitlist seems to move pretty fast): llm keys set typesafe # Paste key And now you can ask yes/no "noul" questions like this: llm -m jev 'Please refund my last payment.' \ -s 'Does this message explicitly request a refund?' Output: {"type": "noul", "noul": 0.99} Or choice questions like this: cat message.txt | llm -m jev \ -s ' Which team should handle this message? If billing and technical issues both occur, choose billing. ' \ -o answer_type choice \ -o criteria ' { "billing":"Charges, invoices,…
This source does not provide full text. Read it at simonwillison.net.