Jev: The Fast, Text-Free AI Built to Sit Beside Your LLM

Jev, from the two-year-old startup TypeSafe AI, is a new kind of AI model that does not write text at all. You hand it a block of state and a fixed set of typed questions, and it answers them all in a single parallel pass — a choice, a score, a yes-or-no probability — in roughly 70 to 500 milliseconds.

Because the legal answers are defined before the call, it cannot return a malformed result: the launch’s “can’t hallucinate” headline. Built by an ex-OpenAI team that helped make ChatGPT, it is a bet that the industry optimised for the wrong customer — humans, not the software that has to decide with no human in the loop.

This episode works through exactly what jev does, why and how it is fast, who built it and the calibration bet behind it, then separates TypeSafe’s own numbers from what independent testing shows — the headline “193x faster” becomes about 16% in a real pipeline, and “can’t hallucinate” means can’t be malformed, not can’t be wrong.

The bigger story is the one jev is a data point in: AI is quietly shifting from one giant model to a system of specialists, where a fast, typed model routes work around a slow, expensive reasoner — with named evidence from Berkeley, Stanford, NVIDIA and Yann LeCun for where that combination pays, and where it does not.

I'm Dan. AI moves too fast to keep up with, so I built my own stack of AI tools to research, analyse, verify and illustrate the questions I can't stop thinking about — mostly to learn it myself, and I share what I find. AI-assisted, fact-checked, worth a second look.

Follow Dan’s AI Intel in whatever app you're listening in — it's free, and a follow is the single biggest thing that helps a small independent show grow. One quick thing, from Dan — I make this show mostly to keep up with AI myself, and I'd love to make it better. If there's something you'd push back on or want me to go deeper on, tell me: [email protected] — I read every one.

The full written report — with the charts, sources and interactive exhibits — is on the site: read it here. Browse every episode and all of Dan's shows at connectiveshift.com.

This show is AI-generated and fact-checked — deeply researched, and worth a second look. Follow Dan's AI Intel — it's free, and the single best way to help a small independent show grow. Thoughts or pushback? [email protected] — I read every one.