| ▲ | dannyw a day ago | |
Qwen3.6 is still the best agentic open weight LLM around 30b params (Gemma isn’t very good at agentic execution). I also find the model is a lot more predictable and less “glitchy” when made to think in Chinese. You can do this in the system prompt. | ||
| ▲ | akazantsev a day ago | parent | next [-] | |
> Gemma isn’t very good at agentic execution I had no issues with it for C++ development with https://pi.dev. I'm yet to try it with Zed Editor. I don't rely on agents too much. However, I used it on Chromium's codebase to research some functionalities, let's say for searching. Requests like: check my last commit and do the same for SetterA and SetterB; it also ran without any errors. | ||
| ▲ | anana_ a day ago | parent | prev [-] | |
Apparently agentic performance in Gemma was improved recently: https://x.com/googlegemma/status/2077449152062247219 Too little too late imo | ||