Thread

1. tecleandor · 1789726540 · focus · HN ↗

   I'm confused... This has no relation with the Jev team, isn't it?

   It's trying to "emulate" Jev behavior using a regular small LLM model (Qwen3 0.6B or MiniCPM5 2B). And with the smallest model it takes like between half to two seconds to run in my M2 Max, so it's not super fast.

   I mean, it's faster than asking to a regular LLM, but I think that's not proper to have Jev on the name (also legally...)

   Edit: no shade, and I'll give it a try for some ideas. I'd also like to have an open weights Jev but I think the naming is misguiding. I also have to try Jev that, BTW, got access pretty quickly, less than a day I think...

   1. CharlieDigital · 1789727513 · focus · HN ↗

      OP's point here is that the overall approach of restricting output token space and using parallel prompts to produce concurrent results and taking the most relevant ones isn't something novel to Jev (not saying there's nothing novel, but a facsimile can be created at the application layer using any small, fast model)

      1. Foobar8568 · 1789728409 · focus · HN ↗

         I still don't get the point of jev....it's basically an optimized models/runner on really short context and output?

         1. orbital-decay · 1789730385 · focus · HN ↗

            It's a specialized classifier model. It classifies input text into categories with a confidence score. Usually those classifiers are small like in the OP but jev is supposedly big, smart, and fast enough to play DOOM by having the scene described in text and classifying it into button presses.

            1. MrYanMYN · 1789805819 · focus · HN ↗

               It is mostly Harness hype. People actually explore the capabilities of classifier models which up until this point weren't touched. You can recreate most of those with LFM 2.5 classifier locally

Unofficial Hacker News client; not affiliated with Y Combinator.