I don't understand how this is different from oai "structured output" (and whatever the similar paradigm was on Sonnet ~3.7 back then) which everyone moved on from. On their gh they say:
"Jev is TypeSafe's closed service for runtime-defined semantic decisions. This project reproduces that interface pattern with open models; it does not reproduce Jev's undisclosed model or training"
As someone else pointed out it isn't actually Jev... can someone enlighten me
It's a non-instruction-tuned classifier model trained on a confidence-aware RL variety that generates its own schema and follows it, with a confidence score output. Think BERT on crack, smart enough to be used as a decision maker (conceptually). They call it "not an LLM" because it's non-generative but of course it's a language model in the same way all non-instruction-tuned classifiers are.
I was a bit skeptical when read the initial pr on it, yesterday ran a test involving ~250M tokens, something we measure went from ~60% to >80% success (with almost no tuning) and at less than 50% cost the low-end LLM was running at, looking at it more seriously now ... the servers are US-only currently I understand and ZDR is by request
wuhhh · · focus · HN ↗
"Jev is TypeSafe's closed service for runtime-defined semantic decisions. This project reproduces that interface pattern with open models; it does not reproduce Jev's undisclosed model or training"
As someone else pointed out it isn't actually Jev... can someone enlighten me
orbital-decay · · focus · HN ↗
mtkd · · focus · HN ↗
seizethecheese · · focus · HN ↗