{"slug": "jev-the-ai-model-that-doesn-t-talk-it-just-decides", "title": "Jev: The AI Model That Doesn't Talk, It Just Decides", "summary": "A developer highlighted Jev, a new System One model from Typesafe.ai that functions as a classification model rather than a large language model, trained via a method called Reinforcement Learning for Calibrated Decisions (RLCD). Unlike LLMs, Jev outputs only binary yes/no or 0/1 decisions in a structured manner without hallucinations, and is described as significantly faster and cheaper than LLMs. The developer noted Jev is suited to AI automation and other tasks requiring fast, reliable classification where wrong answers are unacceptable.", "body_md": "So, yesterday I was doomscrolling YouTube and just saw a video by[Harkirat Singh](https://youtu.be/_aw32rFL680?si=hiEwwTtnxqAbhmSK). This video was about the new System One Model **Jev.**\n\nAfter watching that video, I thought of putting my thoughts on it.\n\nSo, basically, what I understood is that Jev is not an LLM; it is just a classification model trained using a method they call **Reinforcement Learning for Calibrated Decisions (RLCD).**\n\nNow, the biggest difference b/w LLM and Jev is that a normal LLM could give answers to what we are querying for, maybe with some amount of hallucinations, but here in Jev, it only tells whether it's **ok or not (yes or no, 0 or 1)**, similar to classic classification models but in a **structured manner without hallucinations**.\n\nJev is **very fast and way cheaper** than LLMs.\n\nYou can see more differences on this [blog](https://typesafe.ai/blog/introducing-system-one-models-and-jev).\n\nJev can be used for AI automations where, at certain points, classification is required.\n\nOr any other application where a perfect classification or decision needs to be made and there should be no space for wrong answers, and the response should be faster and cheaper.\n\nMore use cases of Jev are listed [here](https://docs.typesafe.ai/concepts/use-case-map).", "url": "https://wpnews.pro/news/jev-the-ai-model-that-doesn-t-talk-it-just-decides", "canonical_source": "https://dev.to/kush0l/jev-the-ai-model-that-doesnt-talk-it-just-decides-4khl", "published_at": "2026-09-20 07:53:10+00:00", "updated_at": "2026-09-20 08:25:04.556285+00:00", "lang": "en", "topics": ["artificial-intelligence", "machine-learning", "ai-products", "ai-agents"], "entities": ["Jev", "Typesafe.ai", "Harkirat Singh", "System One", "Reinforcement Learning for Calibrated Decisions"], "alternates": {"html": "https://wpnews.pro/news/jev-the-ai-model-that-doesn-t-talk-it-just-decides", "markdown": "https://wpnews.pro/news/jev-the-ai-model-that-doesn-t-talk-it-just-decides.md", "text": "https://wpnews.pro/news/jev-the-ai-model-that-doesn-t-talk-it-just-decides.txt", "jsonld": "https://wpnews.pro/news/jev-the-ai-model-that-doesn-t-talk-it-just-decides.jsonld"}}