RELEASE · MODELS · #485
TypeSafe AI unveils Jev, a model that scores predefined options instead of generating text
Startup TypeSafe AI, co-founded by ex-OpenAI researcher Diogo Almeida, introduced Jev, a model designed to return narrow labels and probabilities (judgments) for developer-defined questions rather than free-form text. TypeSafe says Jev responds in 70–500 ms and is very cheap (listed at $0.042 per million input tokens), but its published benchmarks are limited, comparisons use the company's own workflows, and the model's "no hallucination" claim only applies to output structure, not correctness within allowed choices.
KEY POINTS
- Startup TypeSafe AI, co-founded by ex-OpenAI researcher Diogo Almeida, introduced Jev, a model designed to return narrow labels and probabilities (judgments) for developer-defined questions rather than free-form text.
- TypeSafe says Jev responds in 70–500 ms and is very cheap (listed at $0.042 per million input tokens), but its published benchmarks are limited, comparisons use the company's own workflows, and the model's "no hallucination" claim only applies to output structure, not correctness within allowed choices.
- If reliable, Jev's fast, low-cost judgments could enable high-frequency routing and safety checks inside applications, but its quality and real-world performance need independent validation.
WHY IT MATTERS
If reliable, Jev's fast, low-cost judgments could enable high-frequency routing and safety checks inside applications, but its quality and real-world performance need independent validation.
SOURCES & TIMELINE
2Almeida was an OpenAI researcher who helped build the chatbot and then invent reinforcement learning from human feedback (RLHF), the model-training technique perhaps most responsible for our current age of AI. But despite its capabilities, he was disappointed. “We have lightning in a bottle, and yet it is not useful,” Almeida told TechCrunch. “I’ve been battling that problem since then. It took me a while to come to…
Startup TypeSafe AI built a model called Jev that delivers fast judgments inside software instead of writing chat responses. The promised upside is speed and cost, but the limits are tight. Startup TypeSafe AI has introduced an AI model called Jev that takes a different approach than typical chatbots. Instead of generating text, emails, or code, Jev is built to deliver narrow judgments and probabilities inside other…