That there are so many ways to store data on a browser (including exploits) and that they expose so much information about your physical device is a big part of the problem. Even barring that, there are additional ways they can fingerprint a user. While any one thing might not be telling, when you take all of them in combination, it gets frighteningly accurate how easy it is for them to know exactly who you are.

I remember when the term was first coined and it meant something like “asking an llm to code and NOT attempting to validate, fix or correct the outputs yourself. Just keep prompting in natural language until it works.” It was supposed to be a joke - this sort of use hits a wall pretty quickly and illustrates how limited llms can be.

The term has taken off and its meaning is now in flux. I did find it particularly amusing seeing all the LinkedIn lunatics start posting LLM written garbage about “integrating vibe coding Into your workflow” because they thought it was the new buzz word… and I guess they were right.

One of the things that first made me fall in love with the cli was how fast doing things like this was. GUIs are hard, and can crash or use up resources for all sorts of different reasons wholly unrelated to the primary task you are trying to accomplish. Once I got over the learning curve of using the cli (and to be fair I’m still in the process of getting truly comfortable with it) I was able to do things so much faster and with less frustration.

Of course, I also don’t want to neglect that it’s not just a matter of the command line but just how good Linux is in this regard. Windows has a command line too and I hate using that thing.