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 Founder on Model Alignment Before Jev Release
The post cites TypeSafe AI founder Diogo Almeida's talk before Jev's release, arguing that aligning models with human preferences is not a reasonable optimization direction for automated tasks, and says the interview elaborates well on his automation approach.
TypeSafe AI founder Diogo Almeida, in a speech before the release of Jev, should have realized at OpenAI that aligning models with human preferences is an unreasonable optimization direction for automated tasks. So this interview does a great job of elaborating on his automation
· 10 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.
