llm-typesafe 0.1a0

Related reading

1. V

   TypeSafe AI's Jev now available on AI Gatewayvercel.com

   Vercel AI Gateway now offers Jev, a probabilistic decision model that returns typed choices, scores, and booleans instead of raw text. TypeSafe AI reports it runs up to 193× faster and 445× cheaper than standard LLMs, exposed via the experimental evaluate API in AI SDK 7.

   Vercel·vercel.com·Rohan Taneja·7d·2 min·releaseSave
2. H

   Introducing System One Models and Jevtypesafe.ai

   TypeSafe AI announced its first “System One” model, Jev, a non‑text‑generating LLM that outputs type‑safe structured decisions with calibrated probabilities. It claims 40‑200× lower latency (70‑500 ms) and 100‑500× lower cost versus frontier LLMs, no hallucinations, and parallel sampling. The post includes a side‑by‑side demo, a custom “workflow” benchmark comparing Jev to GPT‑5.6/6 and other mod…

   Hacker News front page·typesafe.ai·8d·9 minHN1824480lobste.rs26Save
3. S

   llm-keys-ui 0.1simonwillison.net

   Simon Willison released llm-keys-ui 0.1, a tiny web UI that lets you store LLM API keys on a remote machine and retrieve them via the llm CLI, avoiding pasting keys into chat sessions. It runs with a single uvx command and exposes local network URLs for access.

   Simon Willison·simonwillison.net·3d·1 min·releaseSave
4. S

   Jev introduces a new shape of LLM - System One, aka Decision Modelssimonwillison.net

   Jev is a new “System One” decision model that consumes text and returns numeric probabilities (yes/no, choice, score) instead of generated text, priced at $0.042 / M input tokens with free output. It’s fast, cheap, and suited for classification‑type tasks, but its opaque numeric output raises bias and explainability concerns.

   Simon Willison·simonwillison.net·1d·4 minHN4715Save
5. H

   Typesafe-computer-use drives a Mac toward a goal for 1/50th of a cent per stepgithub.com

   A Python tool for macOS that replaces expensive LLM‑driven UI automation with a cheap, deterministic classifier (TypeSafe) for per‑step decisions, cutting cost by ~150‑300× and latency by ~10‑40× while still handling text entry via a small writer model.

   Hacker News front page·github.com·awlevin·6d·11 minHN8260Save
6. H

   OpenAI is well positioned to fast-follow Jevarcturus-labs.com

   The post argues OpenAI can quickly replicate TypeSafe’s Jev – a classifier‑style LLM that uses token‑level log‑probabilities – by training similar data and folding the capability into its own models, but notes the only real moat might be Jev’s synthetic training data and calibration process.

   Hacker News front page·arcturus-labs.com·17h·12 minHN271196Save