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.
Jev and System 1 Models: A Different Direction Beyond Generation
In this thread, the author suggests that the problem may not lie in text generation itself, and highlights Jev from TypeSafe AI as an example of a System 1 model designed for a different job.
1/ 🧵 We’ve spent years making LLMs better at generating text. But what if the problem was never generation in the first place? This is where System 1 models, like Jev from TypeSafe AI, get interesting. They’re designed for a different job.
· 0 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.
