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.
lifesim-social-1 vs OpenAI Decisions: Jev Model Benchmark
Cris Lenta shares benchmark results: lifesim-social-1 achieves 88% accuracy, 102ms p50 latency, and 0.047 calibration error on social decisions, outperforming OpenAI Decisions API.
we beat OpenAI's Decisions API 24h after it launched it's Jev competitor lifesim-social-1 vs OpenAI Decisions on social decisions: • accuracy: 88% vs 67% • p50 latency: 102 ms vs 278 ms • calibration error: 0.047 vs 0.170 (lower is better) this means agents will not only
· 8 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
