I'd love to know if Jev is still fundamentally LLM-shaped in architecture. Like is it using a single forward pass with a learned readout over the predefined options (i.e. a discriminative head on a transformer, no decoding), or something else? I did similar things for zero-shot criterion-based classification using a 4B Qwen model but could not reach the level of intelligence they've got here. Tho speed/cheapness was similar.
padolsey · · focus · HN ↗