Former OpenAI researcher builds an AI model that judges options instead of writing text
TypeSafe AI launches Jev, a judgment-only model built by ex-OpenAI staff that classifies inputs with 70-500 ms latency instead of generating text.
Startup TypeSafe AI, co-founded by former OpenAI researcher and InstructGPT co-author Diogo Almeida, introduced Jev, a model that scores developer-defined answer options with probabilities rather than generating free-form text. The company claims 70-500 ms responses, parallel multi-question evaluation, and $0.042 per million input tokens with free outputs, targeting request routing, sales intent scoring, and assistant guardrail checks. Benchmarks are self-built and not independently verified, the 'no hallucination' guarantee only covers output structure, and access is currently via waitlist.
- Jev returns predefined labels and probabilities for routing, triage, and guardrail workflows instead of chat responses.
- Claims 70-500 ms latency; pricing listed at $0.042 per million input tokens with no output charge.
- Co-founder Diogo Almeida co-authored InstructGPT; performance tests use TypeSafe-built workflows as references.
- 'No hallucinations' only means outputs stay within preset options; factually wrong choices remain possible.
- Developers get access through a waitlist; competitors like OpenAI Structured Outputs offer similar categorization.
- Vendors
- TypeSafe AI
- Products
- Jev
- Organizations
- OpenAI
- AI models
- Jev
From the original article
3 min read at the-decoder.com
TypeSafe AI, founded by former OpenAI researcher Diogo Almeida, is releasing a model that deliberately generates no text. Instead of chat responses, "Jev" delivers pure classifications for software, with response times starting at 70 milliseconds and extremely low token prices. The approach doesn't protect against mistakes, though.
By Maximilian Schreiner · the-decoder.com
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.