News for hackers. Stuff that matters.
[dead]
Re:Show HN: Jevstiller – Distill Jev into a local model, wit... by wedg_ on Tuesday September 29, 2026 @12:29PM (#49896034)
Woah cool idea. So it's almost a drop-in replacement for a typical Jev setup that just reduces your jev bill over time ?
Re:Show HN: Jevstiller – Distill Jev into a local model, wit... by tgluck on Tuesday September 29, 2026 @03:03PM (#49898707)
Thanks.

Drop-in yes: point TYPESAFE_BASE_URL at it and nothing else changes.

Re:Show HN: Jevstiller – Distill Jev into a local model, wit... by kodefreeze on Tuesday September 29, 2026 @01:02PM (#49896516)
Isn't this against their ToS? Useful for hobby stuff.
Re:Show HN: Jevstiller – Distill Jev into a local model, wit... by KetoManx64 on Saturday October 03, 2026 @12:57AM (#49941459)
Why would it be against the rules to use the previous answers that the AI model gave you within your own project? That's like saying you can't use your Claude code convo history to answer questions within your codebase.
Re:Show HN: Jevstiller – Distill Jev into a local model, wit... by dotancohen on Tuesday September 29, 2026 @01:49PM (#49897433)
It would be great if we could correct Jev's incorrect answers, even on a separate endpoint. Let me tell it what Jev got wrong.

What type of head is that? What type of model is that head part of?

Re:Show HN: Jevstiller – Distill Jev into a local model, wit... by tgluck on Tuesday September 29, 2026 @03:11PM (#49898819)
Not today, but Interesting idea. The main motivation was a drop-in for an existing Jev setup, so the only teacher right now is Jev and the audit measures agreement with Jev. A correction would have to become a second label source that overrides Jev's for that input.

The head is a multinomial logistic regression: one linear layer plus softmax on top of a frozen sentence-embedding model (bge-small by default, swappable). That head is the entire local model, the encoder is off the shelf and never changes.

Re:Show HN: Jevstiller – Distill Jev into a local model, wit... by dotancohen on Tuesday September 29, 2026 @06:59PM (#49901981)
Yeah, I kinda figured that head was the whole model, the way you phrased it. scikit-learn?
Re:Show HN: Jevstiller – Distill Jev into a local model, wit... by tgluck on Tuesday September 29, 2026 @07:08PM (#49902072)
No, plain numpy. It's full-batch Adam on cross-entropy against soft targets, about 80 lines.
Re:Show HN: Jevstiller – Distill Jev into a local model, wit... by dotancohen on Wednesday September 30, 2026 @04:26AM (#49905988)
I'll look into Adam, thank you!
Re:Show HN: Jevstiller – Distill Jev into a local model, wit... by ricardobeat on Tuesday September 29, 2026 @05:50PM (#49901187)
Please don’t post AI generated replies.
Re:Show HN: Jevstiller – Distill Jev into a local model, wit... by dotancohen on Tuesday September 29, 2026 @07:00PM (#49901989)
Why do you think that's AI?