Clef: Open-weight decision models, and new RL fine-tuning platform
Thread
Unofficial Hacker News client; not affiliated with Y Combinator.
Clef: Open-weight decision models, and new RL fine-tuning platform
Unofficial Hacker News client; not affiliated with Y Combinator.
vulture916 · · focus · HN ↗
At 300 tokens per call, you'd get:
One million decisions on Jev cost about $12.60. One million decisions on Clef cost about $72.
Would probably make sense to self-host Clef, if you have the capability/resources. If not...
scronkfinkle · · focus · HN ↗
It's weird to think of these kinds of models as having "output tokens". Cross-encoder approaches like Laya add a [MASK] marker per option, but nothing is generated the way an autoregressive transformer generates. It's one bidirectional pass over your input, then a small head scores each option, so you wouldn't really pay for output as much as only input