When you use AI features, the IDE needs to send your requests and code to the LLM provider. In addition to the prompts you type, the IDE may send additional details, such as pieces of your code, file types, frameworks used, and any other information that may be necessary for providing context to the LLM.
Doesn’t sound like it gives you much transparency or control over the data it sends no matter which feature you use. Sadly not usable at my job then.
That would cover like 80% of my work related usage of chatgpt and do stuff I didn’t think of outsourcing to AI. I’ll probably unsubscribe from co pilot too.
Can’t wait for it to be in Goland.
If you’re willing to use the EAP version, its already there.
Nifty
give me unit test generation and I’m bought
I mean, the inverse is probably more productive. Specify the observable behaviors you want and let the “AI” build the software.
Test Driven AI 🤔
deleted by creator