Nothing, but imagine using LLMs for a classification task
People out there are so resigned to the models being unreliable that they are really doing things like hallucinating deliberately, and then matching the hallucinations to embeddings -
I'm certainly not resigned to that, at least for classification.
Even non-frontier models are absurdly good at this in a broad sense.
Which would make it hard to judge "a model that will never produce unreliable outputs in the first place" against something that is already really, really good and exceptional in domain-specific areas with the tiniest amount of elbow grease.
It would be great to see benchmarks for Jev that demonstrate the value of calibrated uncertainty.
For example, one could set a confidence threshold over which we trust the model decision, and otherwise reject. This provides a lever to trade-off accuracy and automation %.
Then we can ask questions like "What % of decisions can we automate to achieve 90% accuracy"?
i ran some interesting experiments on jev today and wanted to share the results. i compared cost and latency of support ticket triage with different arrival rates for jev vs mainstream LLMs: https://suraj-website-eta.vercel.app/blog/what-a-correct-dec...
People out there are so resigned to the models being unreliable that they are really doing things like hallucinating deliberately, and then matching the hallucinations to embeddings -
https://softwaredoug.com/blog/2026/08/10/hypothetical-classi...
You could do that or you could just... use a model that will never produce unreliable outputs in the first place.