What even is the point of a limit if it's just going to auto-raise? Now you can end up in the situation of owing that. Perhaps you forget that the agent is running in the background somewhere for a while. Or perhaps you end up with a vulnerable dependency that does that for you.
Limits are there to prevent unwanted behaviors, either accidental or malicious.
That is quite the jump. Google Vertex Ai has spend based auto upgrades and I've seen it elsewhere (cannot recall at the moment). So the first is pretty normal, the second seems like another bug (they've had a lot this week and it's not even half done)
What even is the point of a limit if it's just going to auto-raise? Now you can end up in the situation of owing that. Perhaps you forget that the agent is running in the background somewhere for a while. Or perhaps you end up with a vulnerable dependency that does that for you.
Limits are there to prevent unwanted behaviors, either accidental or malicious.
That is quite the jump. Google Vertex Ai has spend based auto upgrades and I've seen it elsewhere (cannot recall at the moment). So the first is pretty normal, the second seems like another bug (they've had a lot this week and it's not even half done)
Kinda wondering if Claude is reporting back on the value of the project it's working on, going "this guy's making money, let's put him on some list"