Jeff – Jev-compatible 0.8B decision models, trained at home, ~30 ms
Thread
Unofficial Hacker News client; not affiliated with Y Combinator.
Jeff – Jev-compatible 0.8B decision models, trained at home, ~30 ms
Unofficial Hacker News client; not affiliated with Y Combinator.
adrithmetiqa · · focus · HN ↗
jubilanti · · focus · HN ↗
Like what am I missing? I use Structured Outputs every day and this just seems like that with fewer steps?
edit: Where I'm coming from, I can triage 10,000 support tickets with deepseek flash for less than $1, and latency is sub 1 second if it needs to be integrated into a live user flow. I don't need anything cheaper or faster than that.
fzysingularity · · focus · HN ↗
The aspect that I like the most is the typesafe API that introduces new probabilistic concepts that are more sound than json schema and constrained decoding with quasi-confidence scores. Developers were asking LLMs to also emit confidences which made absolutely no sense whatsoever.
tclancy · · focus · HN ↗
fzysingularity · · focus · HN ↗
This looks pretty decent: <a href="https://www.aidancooper.co.uk/constrained-decoding/" rel="nofollow">https://www.aidancooper.co.uk/constrained-decoding/