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 solves the LLM JSON parsing problem
The post says Jev solved a problem AI teams have patched for years: parsing LLM JSON output, handling markdown fences, and dealing with inconsistent enum values.
Jev just solved a problem every AI team has been quietly patching for two years. you ask an LLM for JSON. you parse it. you handle the markdown fence. you retry when the enum comes back as "technical support" instead of technical. that second program isn't small - in most
· 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
