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.
TypeSafe Launches Jev System One Model: Structured Queries with Parallel Probability Outputs
TypeSafe introduces Jev System One, which instead of generating text token by token, answers structured questions (urgent? escalate? team?) with probabilities in parallel. Priced at $0.042/M input, free output, ~200x faster and ~400x cheaper.
Jev, TypeSafe's new System One model, could be huge. Instead of an LLM generating text token by token, you ask structured questions (urgent? escalate? team?) and get probabilities back in parallel. $0.042/M input, free output, ~200x faster, ~400x cheaper.
· 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
