> But then again plain LLMs have been perfectly cheap and serviceable as zero-shot classifiers for quite some time now
I'm no prompt engineer, but I've found them to be too slow any time I wanted to use them that way. I have never tried Jev, but apparently it is supposed to be fast, so it seems like, according to the marketing, it could become usable where LLMs haven't been.
I also found inconsistent results (across time and similar inputs) which made it useless for me. I reverted to using LLMs for coding machine learning. I get deterministic outputs that make sense to me, but don’t have to know the ins and outs of how it works (given how it’s applied). I may try Jev in the future for a new problem but unlikely to refactor something that works.
I'm no prompt engineer, but I've found them to be too slow any time I wanted to use them that way. I have never tried Jev, but apparently it is supposed to be fast, so it seems like, according to the marketing, it could become usable where LLMs haven't been.