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 probability bias observations and Jev-Omni OSS variant
A user tests @typesafeai's Jev on dice and card probability questions, noting a bias toward the first option, and mentions their own multimodal OSS variant, Jev-Omni.
Just asked Jev from @typesafeai about a die roll. It said 81% -> 1. A fair die? 81% on 1. A square tile dropped? 97% on edge A. List doesn't end.. Same with Deck of cards.. Seems Jev just likes the first option ! (only for few cases) Our own multimodal OSS variant, Jev-Omni,
· 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
