Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

I think this is overselling their capabilities. I've used Gemma 4 and Qwen 3.6 quite a bit on my strix halo home server. They're great models and the dense variants are significantly better, but they're still very far behind the frontier. If you boot up Gemma 4 MoE and OpenCode/Pi and expect to perform anything like Claude Code or Codex you're going to be very disappointed.


You need to switch out the prompts and work with it differently.

I posted this yesterday https://github.com/day50-dev/petsitter

I use it with https://github.com/day50-dev/simple-llm-cli

And modify the "tricks" until my evals get to good numbers. It's a model by model basis.

This is what the larger firms are doing - they have custom prompts per model


Petsitter's default tricks doesn't seem to do much for Qwen3.6, right? JSON mode could be useful I suppose, but that's not really going to make it better at writing code. Do you have any other example tricks? I'm having a hard time understanding how I would apply them.


thanks for the feedback ... i'll work on publishing them.

I haven't include more sophisticated ones because they are complicated and I wanted to avoid the friction




Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: