Jev versus text-generating models
Jev does not generate free-form text. A side-by-side video compares parallel decision-making with token-by-token text generation.
TypeSafe AI CEO on Jev task design
Diogo Almeida says that in Jev, the task per question is defined in one paragraph, emphasizing that doing the right task matters more than data.
Diogo Almeida, CEO of TypeSafe AI: "doing the right task matters way more than data" he co-wrote GPT-4 and ChatGPT before building Jev, so this comes from someone who trained the models you use every day in Jev the task is one paragraph of text per question, and the wording
· 13 likesOpen on X
More like this
Pricing, evaluations, and the name Jev
The launch thread explains code-and-AI workflow evaluations, the input price announced at launch, and free output tokens.
Jev Model: Decision-Making Probability Generation, 200× Faster and 400× Cheaper Than LLMs
This model is built for decision-making rather than text generation, outputting probabilities for each option in parallel instead of token-by-token responses. The author shares a simplified comparison of normal LLMs versus this Jev model.
