> cause we all know Claude will use 1000 words when 10 will do
Further, the agents are incentivised (if that's the appropriate term here) to do this, since more tokens equals more cost.
> cause we all know Claude will use 1000 words when 10 will do
Further, the agents are incentivised (if that's the appropriate term here) to do this, since more tokens equals more cost.
Tokens used for user-facing prose are a rounding error for coding agents. I don't think there's a conspiracy there.