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 Model: No Chat, Only Three Judgment Types—Is 'Zero Hallucination' Just Wordplay?
The post describes the Jev model as not chatting or writing code, only performing three task types—choice, scoring, and true/false judgment—with pre-enumerated answers, single forward-pass probabilities, and free output, noting its zero-hallucination claim only guarantees valid format.
卧槽，ChatGPT 共同发明人消失两年，回来做了个不会说话的模型。。。 Jev 不聊天不写代码，只答三种题：选一个、打分、是非判断。答案提前枚举，一次前向出概率，输出免费。 但"零幻觉"是文字游戏，只保证格式合法。 你项目里有多少大模型调用，只要一个是非判断？#Jev
· 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.
