You must log in or # to comment.
So Anthropic have made a change that prevented people from wasting tokens? I’m sure they’ll be very keen to reverse that.
Showing the tool call string does not waste tokens.
That’s just how they display information to the user — tool calls no longer show arguments unless they need use permissions, and they’re often hidden entirely being “4 tools called”.
As per the article, knowing when the tool is reading totally unrelated files allows devs to cancel the workflow early before it churns thousands of tokens on output that is based on totally incorrect information
Right, I may have misinterpreted the OP is wasted token in the tool call display, not as you mentioned the correction of issues.
I noticed the new Claude is much less token efficient in general too, so perhaps they’re trying to sell that new 6x more expensive fast mode.
From the article, fourth paragraph:
There’s also a financial impact. If developers spot that Claude is going down a wrong track, they can interrupt and avoid wasting tokens.
@bjorney@lemmy.ca understood what I was referring to, I don’t really understand what you thought I was saying.
I already apologized for the misinterpretation in another comment
AI already writes you garbage, now you can’t even see what it did?
