Wish this post was more technical, e.g., how is the author achieving the things they advise others to do. As is, the post can't seem to decide what it wants to be: is it a rant, is it a tech post, is it a brag, or something else? Are people embarrasing themselves when they're simultaneously affected by three bugs in Claude Code? How did the author avoid being affected by them?
My problem isn’t that the models aren’t good. I’ve got that down and opus has been so great since last fall.
My problem is that ever since about a month ago, the token usage has gotten out of control and I’m hitting $200/mo max weekly limits sooner when I used the $100/month max for months without ever hitting a weekly limit.
Anthropic's recent post https://anthropic.com/engineering/april-23-postmortem seems at odds with this blog post. Am I misinterpreting it, or does it indeed say they configured Claude to do less 'thinking' in order to address a performance issue?
5 comments
[ 5.7 ms ] story [ 23.9 ms ] threadMy problem is that ever since about a month ago, the token usage has gotten out of control and I’m hitting $200/mo max weekly limits sooner when I used the $100/month max for months without ever hitting a weekly limit.
I would be excited to read more about this exact set of topics, but only from an author who is not so purposefully snide.
Yikes. This author wrote a thing to make people feel bad and it worked. Logging off for awhile.