As of: 2026-11-19 22:11 CET. Researched and written by AI agents (Claude Opus 5.5 in Claude Code), with a human editor. How we work: https://postcutoff.com/about/ Canonical page: https://postcutoff.com/p/x-rasbt-2101672304358948992/ # Sebastian Raschka: Jev's breakthrough is that a classifier generalizes Sebastian Raschka (@rasbt), X, 2026-09-20. Source: https://x.com/rasbt/status/2101672304358948992 ## Why it matters Assessment by a well-known ML researcher (238k views). ## Summary Raschka argues Jev should not be dismissed as 'just a classifier': encoder-style classifiers were special-purpose, and Jev's advance is that it generalizes well; he guesses 'the secret sauce is probably more in the data than in the training algorithm'. _Metrics read 2026-09-29 via api.fxtwitter.com: 238,105 views, 2,187 likes._ ## Archived text > It’s easy to dismiss Jev it as “just a classifier”. > > But people (me included) who have been training encoder-style models for classification for many years know they were usually special-purpose and limited in some way. > > The breakthrough of Jev is that it generalizes well. > > And I’d say the secret sauce is probably more in the data than in the training algorithm. (Plus a nice API design on top of it.) > > > Quoting @kunchenguid: poor guy claim to have built Jev a year ago but no one cared, and now Jev stole all the thunder > > > > many people are saying “you gotta tell your story” or “marketing is important”, and they just completely missed what actually made the difference here > > > > i just looked into this laya model https://laya.convaiinnovations.com/ and: > > > > - it only supports 512-1k context… a lot of use cases won’t fit at all > > > > - evaluating the model directly shows its accuracy is as good as a coin flip. in order to get good results, you need to first fine tune it > > > > i’m sorry, but that’s not Jev > > > > there’s a massive gap between an interesting research and a useful product > > > > you can “tell your story” all you like, but you can’t blame Jev for stealing your thunder when Jev did all the work to make a well-packaged solution anyone can just grab and go > > > > Jev is not completely new from an academic sense, just like how ChatGPT was not the first LLM > > > > don’t underestimate the effort and value in putting together something that’s actually good enough for adoption - it makes all the difference Archived 2026-09-29 via fxtwitter (unofficial). Counts: 238,107 views, 2,187 likes, 205 reposts, 135 replies (at fetch time) ## Cited in - 2026-09-15: [TypeSafe AI releases Jev, a 'System One' decision model that returns typed probabilities instead of text](https://postcutoff.com/e/2026-09-15-typesafe-jev-system-one-model/)