Comment by piokoch

My problem with CC is that it is trying to be very creative. I am asking it to fix some test, or create a new test. What it is doing? It is running grep to find all tests in the code base and parses them. This eats a lot of tokens.

Then it runs the test, as if I could not do this myself, it reads the output, sometimes very long (so more and more tokens are burned) and so on.

If people had to pay for this cleverness and creativity an API price, they would be a bit shocked and give up quickly CC.

Using Aider with Claude Sonnet I am eating much less tokens than CC does.