- By not being a optimised for chat, it can deliver confidence for answer and not for how an answer should be phrased
- Speed. It can take seconds for OpenAI to compile schemas, jev can respond before openAI has even begun thinking
- Token efficiency and price. I think its the output token they don't even charge for because they are negligible, and the tokens they do charge for are at a fraction of a comparable model.
If you are using structured output, I think those 3 together is a really big deal.
>But their example is classification but that would also be possible and faster with a classic BERT model.
I believe the things you can classify with ChatGPT without any tuning or training is way beyond what BERT can do.
As far as I understand, the idea of Jev is zero-shot or few-shot classifier: it learns a lot of stuff at pre-training, but unlike a classic LLM it doesn't need to learn how to chat, so it can be much smarter at a particular size
> But their example is classification but that would also be possible and faster with a classic BERT model.
With BERT, you need a large, labeled dataset, and you have to train/fine-tune the model. Jev is pitched as a zero- or 'few-shot' model. You define the schema in code, give it instructions, and it works without a traditional training pipeline.
> So their pitch is a task specific smaller model or am I completely misunderstanding the whole thing?
Yup; that about sums it up: it is more or less an optimized, task-specific small model with the flexible understanding of a traditional LLM.
BERT requires a huge corpus, but it isn't labeled. BERT is trained through self-supervised learning using mask tokens and next sentence prediction. Fine-tuning is useful for specific tasks, but isn't absolutely essential for the model to function.
I think they were responding to this. You can use BERT to provide zero shot classification predictions.
If you accept the premise that there are use cases where you might ask a frontier model a classification-shaped question and expect an ok enough answer, rather than creating a purpose specific classifier on some dataset that you have, then it follows that this is quite an inefficient thing to do, because you're doing extra work to turn the output tokens into a structured output and mostly throwing them away. So then if you could instead train a frontier level model that skips the output tokens and directly returns the structured classification information, that would be more efficient, and that's what jev seems to be.
But a lot rides on that initial premise of whether this is a use case that makes sense. But if you find yourself asking a model like Opus arbitrary yes/no questions and then maybe you switch to a faster and cheaper model because it's too slow and expensive, it seems like jev might be a great replacement for that.
Not particularly. There is still the problem of hallucinations and varying results across runs.
That's more of what type-safety means for their team. Every run gives the same results. It's type-safe
For three choices problem (A,B,C), what Jev guarantees is that it will give the choice in a defined schema (type-safe). It never guarantees that the choice is correct (hallucination).
My base case is that this will probably be pretty useful, and also not as useful as the current hype suggests.