Comment by yndoendo
3 days ago
Started work with OpenCode and my number one issue is that they do not cleanly document how to configure the settings to only run local ML models.
It is all focused on pushing prompts out to 3rd party providers that uses them for training. Irony is having to use the 3rd party provider to properly configure OpenCode with local only ML. I cannot have private information leak.
Good thing I tested it on open source code base before touching property code bases.
Huh ... is that related to why I see little Gemini hits constantly when selecting e.g. DeepSeek 4.1 flash on openrouter? I'm not going private for a bit (mac studio on the way) but when I do I want to lock it down, but pretty stuck on opencode for the moment. If it's leaky that's a problem.