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 2B model approaches Qwen3.5-397B on JevOCRBench with 1/200 parameters
The post claims Jev is the real story: a 2B model scores 93.6 AUROC on JevOCRBench, close to Qwen3.5-397B-A17B's 93.8, and works with any OCR by checking its output.
Jev is the real story. A 2B model scores 93.6 AUROC on JevOCRBench. Qwen3.5-397B-A17B scores 93.8. With roughly 1/200 of the total parameters, Jev achieves a similar AUROC to Qwen3.5-397B-A17B on JevOCRBench. And it doesn’t care which OCR you use. It checks output from
· 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
