May be these comments are actually originating from training annotated data? If I were to add code annotations for training data, I would sort of expect such comments which makes not much value for me but for the model, gives more contextual understanding…
x = 1 // set X to 1
You get:
x = 1 // added this to set x to 1
And sometimes:
// x = 1 // removed this
These comments age really fast. They should be in a git commit not a comment.
As somebody who prefers code to self-describe what it is doing I find this behaviour a bit frustrating and I can't seem to context-prompt it away.