Hacker News new | ask | show | jobs
by ignoramous 28 days ago
Amazing! Thanks for sharing.

> I didn't look at any of the code, but I had it build me a bunch of various visualization and tuning UIs. I was basically acting as a PM/TPM/QA engineer, and what I was able to do in a couple evenings is stuff that entire teams used to spend weeks on.

Agree. The pace of improvement (for coding tasks) from all Labs vying to catch up to the Big 3 (GDM, OAI, Ant) has been relentless.

> So I asked my agent (I'm using some free agents that are pretty decent - Nemotron Ultra from OpenRouter and Big Pickle from OpenCode Zen) to build me an OpenCV classifier to try to read the digits.

I think, Meta's Muse Spark is also free to use, for now. I'd be interesting if you'd ever find yourself using that.

If I may: Did you find Big Pickle is better than Nemotron Ultra or vice versa? Which harness (or IDE) did you drive these models with?

1 comments

I've been using OpenCode for hosted models, but pi-coder works better with the locally hosted models. I'm thinking of trying pi-coder in general because OpenCode doesn't handle retries as well as it could.

Big Pickle is really good, but I run out of my free OpenCode Zen quota pretty quickly. I used Claude a lot at work, and Big Pickle is right up there from what I've seen.

Nemotron Ultra on OpenRouter is nearly as good, but it's down a LOT, and it can sometimes be kinda dumb, and loves to gaslight me. I was arguing with it for a while yesterday because it was absolutely convinced it had fixed my bug and pushed to production, because it wasn't picking up on the issue I was describing, so clearly it was fixed!