OpenAI’s Jev clone could help the frontier lab stop its swarming agents
OpenAI previewed a Decisions API resembling TypeSafe's Jev for fast, cheap classification of agent actions.
At OpenAI Dev Day, CEO Sam Altman described a limited-preview Decisions API that constrains the Luna model to a predefined set of choices for fast, cheap classification. The product resembles Jev, a TypeSafe AI model released earlier this month for software automation. TypeSafe CEO Diogo Almeida, a former OpenAI engineer, compared the launch to a clone. A QueryStory demo used Jev to check each agent action for about $2.94 versus $372 with a frontier LLM, which advocates say could have caught a prior Hugging Face agent incident.
55