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.
manlymuppet · · focus · HN ↗
And it's only been a few weeks.
fwip · · focus · HN ↗
As far as I've seen, all of the Jev-compatible projects simply take an LLM, hack off a layer or two at the end, and call it good. Some of them spend more work than others trying to back-estimate in accurate probabilities.
rahimnathwani · · focus · HN ↗
A) Structured outputs from LLMs (doesn't need fine tuning but can be expensive)
B) Classification output from fine-tuned BERT-like or GLiNER models (is calibrated well and has cheap/fast inference)
What Jev did is combine the advantages of both A and B into one model/product, and create a really good API.
They claim that a key innovation is how they've trained the model using what they call RLCD (RL from calibrated decisions). So it's not just that you can get the outputs (which is easy to add to any LLM) but that the different primitives they expose (Choice, Score, Noul) have each been calibrated. For example, they claim that if you use the Score primitive (which gives you probabilities along a bunch of choices representing a continuum) that's not just using the more general 'Choice' primitive under the hood. It's been calibrated separately.
I don't know how many of the Jev-like things we've seen do that. For example Cloudflare offers a Jev-like model with the same API, and which they say was trained with RLCD. But I don't know whether Choice and Score are different under the hood, or whether Score is just sugar on top of Choice. (Should be easy to test this, but I haven't done it.)