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
No idea at all what this particular project called openjev is doing, but <a href="https://github.com/TheoLeeCJ/openjev" rel="nofollow">https://github.com/TheoLeeCJ/openjev and <a href="https://github.com/ekzhang/openjev-sglang" rel="nofollow">https://github.com/ekzhang/openjev-sglang (neither of which I have any relation to) generate a single token, rather than JSON structured output. I wrote up this technique here: <a href="https://sgnt.ai/p/jev/" rel="nofollow">https://sgnt.ai/p/jev/
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
petesergeant · · focus · HN ↗
wuhhh · · focus · HN ↗