I often push past 300k or so and I’ve absolutely worked at 800k but it’s an observable problem. Large context windows can work depending on the problem but I do feel more effective biasing towards small ones <300k.
They claim that they do not charge you anything. So, how can they scam you? Of course, besides your hours and the potential outcome (code). Just curious.
My status line shows 5h and 7d quota usage among other things like model, context usage, git branch, etc. Unfortunately the whole status line disappears half of the time from CC’s broken ass UI.
Personally I have multiple instances of Claude on my PC dedicated to different areas (split between my private subscription and my work one) and it is useful to see both at a glance. And I don't have to keep the terminal open to see how much time is left for quota to be reset. But for single-Claude users this is indeed a valid solution!
Lots of people are gambling on AI with big bucks. Some of it is promising but all those bets won’t pay off. I like to think of this mindset as being the human slot machine that people are shoving money into.
This is a confusion that you could not have predicted, but primed by your comment, I expected "terminal star" to refer to a suggested predecessor of the AI rockstar. No, it refers to the animated Claude Code star :P
reply