TypeSafe AI's Jev model draws strong developer demand

TypeSafe AI, founded by former OpenAI researcher Paul Christiano Almeida, released the Jev transformer, which outputs calibrated probabilities instead of text. The model cannot hallucinate, output tokens are free while input tokens are billed in billions, and demand briefly overwhelmed its API.

• Jev is not an LLM: it outputs probabilities, not text, so it cannot hallucinate
• Output tokens are free; input tokens are billed per billions
• Vercel replaced ChatGPT Luna 5.6 with Jev: 5-18x faster and more accurate
• Model trained only on synthetic data using RLCD