Post

same, i just use a synthetic sample and keep the real data offline

How do you make the synthetic sample?

Local models. Nothing leaves your machine. LM Studio or Ollama run them, also as a service that e.g. RStudio or positron can hook in. Open weights such as qwen3.8 are pretty good.

When you say that RStudio or Positron can hook into local models, how does that work exactly?

Both LM Studio and Ollama run / can run as a service that gets accessed via a localhost url and port (it's actually an OpenAI compatible setup). The IDEs (just like any other service: pi, openclaw, ...) connect to that under their settings. For positron you may have to edit a JSON file.