TypeSafe AI's Jev Returns Calibrated Probabilities, Not Text
TypeSafe AI's new System One model Jev outputs typed, calibrated probabilities for typed questions, with free output tokens and a low input price.
TypeSafe AI has released Jev, a System One model that takes typed questions and returns typed, calibrated decisions as probabilities instead of generating text. The company positions it as a machine-readable alternative to chat-style outputs for applications that need structured answers.
Pricing is notable: input costs $0.042 per 1M tokens, and output tokens are free. That puts the cost on the query rather than the response. The announcement includes vendor benchmarks, but TypeSafe also flags caveats, so developers should treat the numbers as vendor-reported.
Developers are already building on the API, according to the announcement. Since there is only one source, there are no independent results or differing views to compare; the claims are TypeSafe's own.
Sources · 2
More in AI & ML
Jev Creator on System One Models for Production, Not AGI
TypeSafe AI CEO Diogo Almeida, lead creator of Jev, argues System One models belong in production rather than on an AGI pedestal.
Meta's Muse AI Assistant Has a 0-Day That Lets Attackers Hijack It
A newly reported vulnerability in Meta's Muse AI assistant can be exploited with a simple ClickFix attack to take full control of the agent.
Pruning LLMs by Removing Blocks as an Ising Optimization Problem
A new approach frames large language model pruning as a physics-style Ising optimization to decide which blocks to remove.
NVIDIA: AI Security Needs Engineering, Not Just Policies
NVIDIA argues that securing AI agents requires treating security as an engineering discipline with requirements, controls, owners, and evidence.