I'm not a computer science guy, but I had a play with Jev and found it impressive. It allowed me to offer non-technical researchers the ability to classify arbitrary things their participants enter, without prior training or classification, at near instant speed, and negligible cost. My users may find that very helpful in the qualitative research world.
I showed them an innocuous working example of how they could classify thousands of participant entries as "mentioning Italian food" whether it mentioned "pasta", "penne", "rigatone", etc etc. Jev did this task with high confidence, and showed it could differentiate between the inverse, eg had very low confidence when I switch entry to mentioning "hamburgers". I find that a very useful tool to pass on to non-technical colleagues.
But on HN, there are lots of much more qualified people saying Jev is a con, a step backwards, or bonkers that people are impressed. Will one of them tell me plainly what software was doing this prior to Jev, and the like? I don't doubt it existed, but I never came across it. I'm interested to hear from people more expert than myself.
To be precise, software must be able to:
- Classify thousands of entries with arbitrary themes or topics, even if entry doesn't mention that theme or topic directly, with high enough confidence to be useful.
- Do it with thousands of entries in 0-3seconds.
- Do it at negligible cost, eg sub 0.1cents
BeRT, BART and FLAN-T5, for text classification. All of those models are ~half a decade old now, are based on the transformer model, and small enough to run locally. They're not perfectly SOTA, but perform quite well in embedded applications. Fine for low-stakes stuff, I think.
Image classifiers are a hugely competitive space. You've got BeiT, DeiT, MobileOne, ConvNext, FastViT and several more models that all support image classification pipelines.
Thanks for quick reply. I downloaded FLAN for comparison and you are quite right, gives similar results, with the benefit of privacy and self-sovereignty in serving the model.
So other than untestable claims of _how_ Jev generates responses, it's main feature right now is its API design?
A lot of the hate is in the same spirit of the infamous hacker news comment discounting Dropbox because you can just setup an FTP server to do the same thing[1]
In this case, its people who have built BERT classifiers for years, pointing out you can just fine-tune some model to classify. Of course that's true, and still have value, but its not exactly turnkey. And Jev is surprisingly high quality at what its built for.
I showed them an innocuous working example of how they could classify thousands of participant entries as "mentioning Italian food" whether it mentioned "pasta", "penne", "rigatone", etc etc. Jev did this task with high confidence, and showed it could differentiate between the inverse, eg had very low confidence when I switch entry to mentioning "hamburgers". I find that a very useful tool to pass on to non-technical colleagues.
But on HN, there are lots of much more qualified people saying Jev is a con, a step backwards, or bonkers that people are impressed. Will one of them tell me plainly what software was doing this prior to Jev, and the like? I don't doubt it existed, but I never came across it. I'm interested to hear from people more expert than myself.
To be precise, software must be able to: - Classify thousands of entries with arbitrary themes or topics, even if entry doesn't mention that theme or topic directly, with high enough confidence to be useful. - Do it with thousands of entries in 0-3seconds. - Do it at negligible cost, eg sub 0.1cents
You're allowed to be excited about new technology.
What are you allowed to feel when it's old technology?
Anything you want. Do as you please, stop waiting for the internet to tell you how to feel about things.
BeRT, BART and FLAN-T5, for text classification. All of those models are ~half a decade old now, are based on the transformer model, and small enough to run locally. They're not perfectly SOTA, but perform quite well in embedded applications. Fine for low-stakes stuff, I think.
Image classifiers are a hugely competitive space. You've got BeiT, DeiT, MobileOne, ConvNext, FastViT and several more models that all support image classification pipelines.
Thanks for quick reply. I downloaded FLAN for comparison and you are quite right, gives similar results, with the benefit of privacy and self-sovereignty in serving the model.
So other than untestable claims of _how_ Jev generates responses, it's main feature right now is its API design?
A lot of the hate is in the same spirit of the infamous hacker news comment discounting Dropbox because you can just setup an FTP server to do the same thing[1]
In this case, its people who have built BERT classifiers for years, pointing out you can just fine-tune some model to classify. Of course that's true, and still have value, but its not exactly turnkey. And Jev is surprisingly high quality at what its built for.
1 - https://news.ycombinator.com/item?id=9224