maybe you entered the AI space during the vibecoding era but there had been ton of useful models before that. especially zero shot models- both for text and images.
Everything you said here is false. No, I didn't enter the AI space during the vibe coding era. I was training custom ML models back in 2017. And no, there haven't been models comparable to Jev before Jev was published.
Jev is:
- accurate
- general purpose
- fast and cheap
Models we had before Jev had at most 2/3 of above qualities, but none of them were 3/3.
Maybe you are a good person to ask my question then. I have not looked into Jev much, but is it much different from using a regular LLM and constraining its token output to the action space? (e.g. like using llama.cpp's GBNF grammars). Is it just that Jev's "confidence scores" are significantly better than the softmaxed logits? Or is there something else I am missing?
> Models we had before Jev had at most 2/3 of above qualities, but none of them were 3/3.
You're the one being deceptive here. Jev is trading accuracy, speed, and cost for generality. It's less accurate, slower and more expensive than trained classifiers. So it's still 2 out of 3, but with decimals. Maybe 2.2 out of 3 if I'm being charitable.
And the reason we didn't have that before is because nobody thought it's a good tradeoff.
maybe you entered the AI space during the vibecoding era but there had been ton of useful models before that. especially zero shot models- both for text and images.
Everything you said here is false. No, I didn't enter the AI space during the vibe coding era. I was training custom ML models back in 2017. And no, there haven't been models comparable to Jev before Jev was published.
Jev is:
- accurate
- general purpose
- fast and cheap
Models we had before Jev had at most 2/3 of above qualities, but none of them were 3/3.
Maybe you are a good person to ask my question then. I have not looked into Jev much, but is it much different from using a regular LLM and constraining its token output to the action space? (e.g. like using llama.cpp's GBNF grammars). Is it just that Jev's "confidence scores" are significantly better than the softmaxed logits? Or is there something else I am missing?
3 replies →
> Models we had before Jev had at most 2/3 of above qualities, but none of them were 3/3.
You're the one being deceptive here. Jev is trading accuracy, speed, and cost for generality. It's less accurate, slower and more expensive than trained classifiers. So it's still 2 out of 3, but with decimals. Maybe 2.2 out of 3 if I'm being charitable.
And the reason we didn't have that before is because nobody thought it's a good tradeoff.
5 replies →
>>I was training custom ML models back in 2017
but you truly do sound like an angry 19 year old from your arguments.
- accurate - on what? on trust me bro benchmarks?
- zero-shot model are fundamentally general purpose.
- fast and cheap ; models on hf are FREE and fast enough.
1 reply →
I think it is clear he is referring to zero shot classifiers with an LLM backbone. That tech has existed for a long time.