Jev launches: a System One model for decisions
TypeSafe founder Diogo Almeida introduces Jev, its RLCD training method, and its focus on software decisions. The post includes a 2:56 launch video.
Jev System One Model Outperforms GPT-6 Astra and Fable 5.1 on Comprehension Test
Angus benchmarks @typesafeai's new Jev "System One Model" on a 28-question comprehension test, with Jev leading at 100% accuracy and 1.0s, ahead of GPT-6 Astra and Fable 5.1, plus GPT-4o mini as a control.
Benchmarked @typesafeai's new #Jev "System One Model" against GPT-6 Astra and Fable 5.1 on a 28-question comprehension test: 🥇 Jev: 100% accurate, 1.0s 🥈 Astra: 100%, 8.8s 🥉 Fable 5.1: 100%, 10.7s Added GPT-4o mini as a control: 4.1s, but made mistakes. What we building?
· 0 likesOpen on X
More like this
TypeSafe announces access to Jev
TypeSafe’s official account ends its stealth phase, invites developers to request access, and quotes the founder’s launch post.
ChatGPT Co-Inventor Launches Jev: An AI That Only Makes Decisions, Not Words
The co-inventor of ChatGPT has launched a new kind of AI called Jev, claimed to be 20-200x faster and 40-400x cheaper, with free output tokens forever, and it only makes decisions instead of writing text. Link
