|
|
|
|
|
|
by stephantul
102 days ago
|
|
|
Tokens saved should not be your north star metric. You should be able to show that tool call performance is maintained while consuming fewer tokens. I have no idea whether that is the case here. As an aside: this is a cool idea but the prose in the readme and the above post seem to be fully generated, so who knows whether it is actually true. |
|
|
"We measured this. Not estimates — actual token counts using the cl100k_base tokenizer against real schemas, verified by an automated test suite."