Voices
Adam Argyle calls Jev a next-generation programming model, not a tool, and ships an agent-art playground to prove it
Argyle's September 17 post argues the interesting property is not speed but that it makes common-sense judgments over unstructured data cheap enough to run several times a second, which inverts the usual arrangement: code owns the workflow and the model handles narrow structured decisions. He built a playground on the idea, an 'agent assisted art' demo where you edit the dataset and watch the question scores move. Coming from a browser-platform engineer rather than an AI researcher, it is a useful signal of who this model class is actually landing with.
↳ Follow the thread