> The noticeable spike [~20 percentage points] in May in the figure above [tool invocations] was largely attributable to one sizable account whose activity briefly lifted overall volumes.
The fact that one account can have such a noticeable effect on token usage is kind of insane. And also raises the question of how much token usage is coming from just one or five or ten sizeable accounts.
The fact that one account can have such a noticeable effect on token usage is kind of insane. And also raises the question of how much token usage is coming from just one or five or ten sizeable accounts.