conv.

All stories
AIQuiet 6d · day 7

Sebastian Raschka on Jev: impressive classifier generalizing beyond narrow use

Machine learning researcher argues Jev's real breakthrough is in generalization and data quality, not novel algorithmic approaches.

newest coverage 6d agosummary written 5d ago3 pieces6 likes & upvotes XHacker News

What to know

  • Jev is a classifier model that has drawn both enthusiastic demos and critical dismissals in recent days.
  • Raschka argues the real innovation is broad generalization capability and superior training data, not novel algorithms—an execution-over-novelty pattern seen in Stable Diffusion and ChatGPT.
  • The model's exact architecture and training method remain undisclosed, limiting assessment of technical specifics.

Sebastian Raschka Machine learning researcher

Sebastian Raschka on Jev: impressive classifier generalizing beyond narrow use
x.com

How it unfolded 3 developments, newest first · click a bar or a number to jump posts

Peak 1 piece in two hours at Sep 20, 10 AM; 3 pieces over 7 days (3 posts) Sep 20, 10 AM — 1 piece · 1 post — X 1Sep 20, 12 PM — quietSep 20, 2 PM — quietSep 20, 4 PM — 1 piece · 1 post — Hacker News 1Sep 20, 6 PM — quietSep 20, 8 PM — quietSep 20, 10 PM — quietSep 21, 12 AM — quietSep 21, 2 AM — quietSep 21, 4 AM — quietSep 21, 6 AM — quietSep 21, 8 AM — 1 piece · 1 post — Hacker News 1Sep 21, 10 AM — quietSep 21, 12 PM — quietSep 21, 2 PM — quietSep 21, 4 PM — quietSep 21, 6 PM — quietSep 21, 8 PM — quietSep 21, 10 PM — quietSep 22, 12 AM — quietSep 22, 2 AM — quietSep 22, 4 AM — quietSep 22, 6 AM — quietSep 22, 8 AM — quietSep 22, 10 AM — quietSep 22, 12 PM — quietSep 22, 2 PM — quietSep 22, 4 PM — quietSep 22, 6 PM — quietSep 22, 8 PM — quietSep 22, 10 PM — quietSep 23, 12 AM — quietSep 23, 2 AM — quietSep 23, 4 AM — quietSep 23, 6 AM — quietSep 23, 8 AM — quietSep 23, 10 AM — quietSep 23, 12 PM — quietSep 23, 2 PM — quietSep 23, 4 PM — quietSep 23, 6 PM — quietSep 23, 8 PM — quietSep 23, 10 PM — quietSep 24, 12 AM — quietSep 24, 2 AM — quietSep 24, 4 AM — quietSep 24, 6 AM — quietSep 24, 8 AM — quietSep 24, 10 AM — quietSep 24, 12 PM — quietSep 24, 2 PM — quietSep 24, 4 PM — quietSep 24, 6 PM — quietSep 24, 8 PM — quietSep 24, 10 PM — quietSep 25, 12 AM — quietSep 25, 2 AM — quietSep 25, 4 AM — quietSep 25, 6 AM — quietSep 25, 8 AM — quietSep 25, 10 AM — quietSep 25, 12 PM — quietSep 25, 2 PM — quietSep 25, 4 PM — quietSep 25, 6 PM — quietSep 25, 8 PM — quietSep 25, 10 PM — quietYesterday, 12 AM — quietYesterday, 2 AM — quietYesterday, 4 AM — quietYesterday, 6 AM — quietYesterday, 8 AM — quietYesterday, 10 AM — quietYesterday, 12 PM — quietYesterday, 2 PM — quietYesterday, 4 PM — quietYesterday, 6 PM — quietYesterday, 8 PM — quietYesterday, 10 PM — quietToday, 12 AM — quietToday, 2 AM — quietToday, 4 AM — quietToday, 6 AM — quietToday, 8 AM — quietToday, 10 AM — quiet 123
Sep 21Sep 22Sep 23Sep 24Sep 25yesterdaynow · 12:55 PM ET
  1. 3

    Raschka reiteratesGeneralization and data are Jev's real innovation

    The analysis gains traction on Hacker News. Raschka reinforces that while encoder-style classification models are not new, Jev's success in applying them broadly—combined with strong API design—mirrors prior AI breakthroughs where execution and training data, not algorithmic novelty, made the difference.

    “Yeah, it's not the first project where someone applied RL to a (likely) non-autoregressive, encoder-style model. But what's impressive is that it works and generalizes so well, which can make all the difference.”
    — Sebastian Raschka
  2. 2

    Raschka details engineering and data as Jev's competitive edge

    Raschka expands analysis arguing Jev's impressive generalization—classifying emails, playing video games, trading stocks—stems from superior training data and API design rather than algorithmic novelty. He compares the pattern to Stable Diffusion and ChatGPT, where proven techniques achieved breakthrough results through data quality and execution.

    “Jev's impressive breakthrough is that it generalizes so well (you can use it to classify emails, play video games, trade stocks…).”
    — Sebastian Raschka
  3. 1

    Raschka publishes analysis of Jev's classification breakthrough

    Sebastian Raschka posts initial commentary on Jev, positioning the classifier between hype and dismissal.

    • It's easy to dismiss Jev it as “just a classifier

      @rasbtX7d agoview on X ↗