Build your own decision model

bellajbadr

Is this only about getting fix json output?

howunfortunate

As an MLE who has been failing to get anyone interested in classifiers for many years, the hype around Jev makes me scream internally. Yes, I get that a zero-shot classifier is more convenient than the traditional kind, it's very cool. Kind of. But then again plain LLMs have been perfectly cheap and serviceable as zero-shot classifiers for quite some time now, so again I'm back to my internal screaming.

demibabs

Is simply changing the temperature so that the model appears calibrated over a particular benchmark after the fact “allowed”? Feels p-hacking esque.

ursaguild

This is really cool to see. Being able to play the token generation was awesome. Amazing job with breaking down how to think about these models. This made the idea of Jev/decision models really easy to grasp for me. The idea of calibrating the model was helpful. I thought this was a great overview.

sva_

Does someone have examples of interesting stuff that has been built utilizing Jev/decision models? The way this is hyped up surely there must be some good stuff?

nico

This is very cool. If you are looking for something similar but more lightweight, that you can run (and train) on CPU, try out Jeffy: https://jeffyclassify.com/ On GitHub: https://github.com/nicobrenner/jeffy

ford

These are neat - and the source of the many Jev clones we've seen. I think their recent funding round is in part because of their algorithms/data. It remains to be seen if that's a big enough edge to be worth 1 billion+ dollars

sn0n

I saw Jev and without understanding it said to myself, “I can build that!” And brainstormed some weird Alex trebek jeopardy generator I called trebek, a bun ran typescript app that you give it an input, it decides if it’s a category, question or answer then generates what’s missing. Trained a SQLite-vec database on the English language for a few days with a small qwen embedding model to add vec embeds to the db then ripped the cord on the embeddings before I started feeding my llm the proper specs for Jev and now i have a cool jeopardy generator that now doubles as a Jev clone classifier with a custom v1 endpoint for system 0 or whatever it is. Level understanding here, fun experiment though ^>^ and produces useful outputs

fuddle

I'm looking forward to a "Build a Decision Model (From Scratch)" book.

sachaa

This is a great way to start but the perf of LLM models like Qwen are not ideal for local execution. I have adapted Laya (pure decision model) to run in a browser and I am able to get responses under 200ms. Give it a try: https://wexare-ai.github.io/browser-laya/

vivzkestrel

- i have to keep scrolling down on your home page https://nishtahir.com/ to see what posts you have - could you kindly put all that in a /blog page with pagination and not infinite scroll?

mehar_pro

What if Jev is something more than a classifier? There's so much potential here waiting to be seen. I built my own Jev, then realized it could literally run on a webpage. So then I turned it into an npm library https://genclass.dev