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 Decision Model: LLM Generates, Jev Decides
The post explores how Jev works as a decision model: most AI systems make a single LLM sort, route, judge, reason and write, while the Jev guide proposes a split—the LLM generates and Jev decides. It also covers where the decision model sits in a system and what the guide does not prove.
🧵 Most AI systems ask one big LLM to sort, route, judge, reason and write. OpenAI's guide on Jev proposes a split: an LLM generates, Jev decides. Here is how a decision model works, where it sits in a system, and what the guide does not prove.
· 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.
