conv.

All stories
AIQuiet 11d · day 12

Former OpenAI researcher launches Jev, a classification-only AI model

TypeSafe AI's Diogo Almeida releases a model that judges preset options instead of generating text, targeting speed and cost in software workflows.

newest coverage 11d agosummary written 7d ago2 pieces Newswires

What to know

  • Jev abandons text generation entirely, instead scoring inputs against preset developer-defined options—a narrower but potentially faster approach than general chatbots.
  • Response times (70–500 ms) and pricing ($0.042 per million input tokens) are designed to undercut existing models, but performance claims rely on internal benchmarks without independent verification.
  • The model's no-hallucination guarantee applies only to output format, not factual accuracy—it cannot produce invalid category labels, but cannot verify whether the classification itself is correct.
  • Use cases center on software routing and decision-making (customer service triage, refund eligibility checks) where speed and cost matter more than conversational ability.

“TypeSafe says Jev delivers answers in 70 to 500 milliseconds, many times faster than even the fastest current language models.”

The Decoder, Publication · The Decoder ↗

Diogo Almeida Co-founder and CEO of TypeSafe AITypeSafe AI AI startup

Former OpenAI researcher launches Jev, a classification-only AI model
The Decoder

How it unfolded 1 development · click the chart to see its coverage articles

Peak 1 piece in 3h at Sep 16, 12 AM; 2 pieces over 12 days (2 articles) Sep 16, 12 AM — 1 piece · 1 article — Newswires 1Sep 16, 3 AM — quietSep 16, 6 AM — quietSep 16, 9 AM — 1 piece · 1 article — Newswires 1Sep 16, 12 PM — quietSep 16, 3 PM — quietSep 16, 6 PM — quietSep 16, 9 PM — quietSep 17, 12 AM — quietSep 17, 3 AM — quietSep 17, 6 AM — quietSep 17, 9 AM — quietSep 17, 12 PM — quietSep 17, 3 PM — quietSep 17, 6 PM — quietSep 17, 9 PM — quietSep 18, 12 AM — quietSep 18, 3 AM — quietSep 18, 6 AM — quietSep 18, 9 AM — quietSep 18, 12 PM — quietSep 18, 3 PM — quietSep 18, 6 PM — quietSep 18, 9 PM — quietSep 19, 12 AM — quietSep 19, 3 AM — quietSep 19, 6 AM — quietSep 19, 9 AM — quietSep 19, 12 PM — quietSep 19, 3 PM — quietSep 19, 6 PM — quietSep 19, 9 PM — quietSep 20, 12 AM — quietSep 20, 3 AM — quietSep 20, 6 AM — quietSep 20, 9 AM — quietSep 20, 12 PM — quietSep 20, 3 PM — quietSep 20, 6 PM — quietSep 20, 9 PM — quietSep 21, 12 AM — quietSep 21, 3 AM — quietSep 21, 6 AM — quietSep 21, 9 AM — quietSep 21, 12 PM — quietSep 21, 3 PM — quietSep 21, 6 PM — quietSep 21, 9 PM — quietSep 22, 12 AM — quietSep 22, 3 AM — quietSep 22, 6 AM — quietSep 22, 9 AM — quietSep 22, 12 PM — quietSep 22, 3 PM — quietSep 22, 6 PM — quietSep 22, 9 PM — quietSep 23, 12 AM — quietSep 23, 3 AM — quietSep 23, 6 AM — quietSep 23, 9 AM — quietSep 23, 12 PM — quietSep 23, 3 PM — quietSep 23, 6 PM — quietSep 23, 9 PM — quietSep 24, 12 AM — quietSep 24, 3 AM — quietSep 24, 6 AM — quietSep 24, 9 AM — quietSep 24, 12 PM — quietSep 24, 3 PM — quietSep 24, 6 PM — quietSep 24, 9 PM — quietSep 25, 12 AM — quietSep 25, 3 AM — quietSep 25, 6 AM — quietSep 25, 9 AM — quietSep 25, 12 PM — quietSep 25, 3 PM — quietSep 25, 6 PM — quietSep 25, 9 PM — quietYesterday, 12 AM — quietYesterday, 3 AM — quietYesterday, 6 AM — quietYesterday, 9 AM — quietYesterday, 12 PM — quietYesterday, 3 PM — quietYesterday, 6 PM — quietYesterday, 9 PM — quietToday, 12 AM — quietToday, 3 AM — quietToday, 6 AM — quietToday, 9 AM — quietToday, 12 PM — quietToday, 3 PM — quietToday, 6 PM — quiet 1
Sep 17Sep 18Sep 19Sep 20Sep 21Sep 22Sep 23Sep 24Sep 25yesterdaynow · 9:46 PM ET
  1. 1

    TypeSafe AI releases Jev classification model

    Startup TypeSafe AI, founded by former OpenAI researcher Diogo Almeida, launches Jev, a model designed to classify inputs against developer-defined options rather than generate text. The model targets speed (70–500 milliseconds response time) and cost ($0.042 per million input tokens) for use in software workflows like customer service routing.

    “Instead of generating text, emails, or code, Jev is built to deliver narrow judgments and probabilities inside other programs.”
    — The Decoder
    1. 1 outlet Former OpenAI researcher builds an AI model that judges options instead of writing text

      first by The Decoder, 11d ago