alt Hacker NewsI'm not exactly following through with the claim, can someone explain how the built-in classification would not necessitate more tokens used, or be much different from turning on reasoning? Not that I don't see the difference, I just doing see how OpenAI would do it well.
Replies
It's hard to say without knowing their architecture, but I'd guess something like block attention. You can process the prompt separately from the classifications into a latent space and then do some kind of late interaction with the encodings from the classifications.
There are plenty of other ways to do zero shot classification that would result in more "token usage" (really just having to reprocess everything for each class), but the pricing and the way they describe it narrows it down somewhat.
Normal LLM will do the classification on the text that is generated. Jev just returns the classification and confidence.
It has the advantage of speed and the confidence not being hallucinated.
But LLMs start to generalise on the pattern, rather than the classification that you want the more examples you have to train on.
LLMs start to break down as well the more classifications you have. Laya (Open source paper Jev is based on) even mentions that over 20 classifications and it starts to fail rapidly.
20 is around the level of sentiment analysis or minor intent routing. There are cheaper, smaller and easier ML models for that level of classification.
I think the idea is that the latent thinking space in the LLM will be roughly the same for similar quality results - so the majority of executing well could be stripping back and fine tuning an existing LLM.
The claim of how they are doing it is likely wrong.... if you had to bet, it's likely an encoder model of some sort.
AFAIK Jev is nothing special technically so it's easy to embed it as an another tool for the LLM? For many batch tasks it can still be quite a token saver I think.
Or they can even offer it as a standalone API if deemed worth it.