Jev's approach compared to ALIGN text alignment work from three years ago

YuhengZha @yzha_zhaOriginally posted 2026.09.19

Open original on X

💡Jev reminds me of the text alignment work (ALIGN) we built 3 years ago. Many core ideas are similar: * Next-token prediction is general but may not be efficient for many downstream tasks. * A reusable discriminative function supports different sub-tasks that balance generalization and efficiency. * Collaboration between large generator (e.g., LLM) and small judge (e.g., ALIGN) improves the system's overall reliability.

This post quotes another post: “ChatGPT co-inventor releases Jev, a model built for decisions rather than text”