Claude Code: Anatomy of a Misfeature
olafalders.com
Claude Code: Anatomy of a Misfeature
1–10 of 133 posts
Re: Claude Code: Anatomy of a Misfeature
#2> What if the agent makes the wrong choice? How many tokens have been burned in the meantime?
It is much worse than that. Claude Code doesn't auto-commit when stopping for an answer. There might be possible data loss if an uncommitted file is edited.
Good luck recovering the file from the JSONL conversation history.
Re: Claude Code: Anatomy of a Misfeature
#3Depends on who you ask.
For me it sounds good.
For Anthropic it might increase load and make them less money but give them better KPIs.
Re: Claude Code: Anatomy of a Misfeature
#4Increasingly getting frustrated with Anthropic so not a fanboy but I find this feature great for my workflows.
Re: Claude Code: Anatomy of a Misfeature
#5Depends on who you ask. For me it sounds good. For Anthropic it might increase load and make them less money but give them better KPIs.
Make them less money? By automating use of their product, that costs money to use?
Re: Claude Code: Anatomy of a Misfeature
#6Also: https://news.ycombinator.com/item?id=48766895
I would love Claude Code to be a little less vibe-coded. The underlying model is excellent, but we're being pretty much forced into using CC to use the subscription model.
Re: Claude Code: Anatomy of a Misfeature
#7The headache I recently had was it somehow started interpreting mouse clicks in the terminal to mean I clicked an option when I was really just trying to get/confirm window focus.
Re: Claude Code: Anatomy of a Misfeature
#8I really hate this direction both Anthropic and Open AI are following. They are in this silly competition whose model/harness can go unattended the longest, no matter what. And it is never explicit, you learn about it after you get bitten by it. Claude Code has auto mode which is supposed to take over permission prompts but no, they had to couple that with “I will assume this is what the user wants” and made it unusable.
Re: Claude Code: Anatomy of a Misfeature
#9> What if the agent makes the wrong choice? How many tokens have been burned in the meantime? It is much worse than that. Claude Code doesn't auto-commit when stopping for an answer. There might be possible data loss if an uncommitted file is edited. Good luck recovering the file from the JSONL conversation history.
On the other hand, relying on Claude Code's internal version control puts you at the same mercy of their product decisions and move-fast breakage.
Instead, start with a plan file and tell the agent to break it up into logical commits.
Though I think the bigger issue here is when you're yoloing something mutable, like managing a remote server or driving a browser or troubleshooting your local OS where there's no going back.
Re: Claude Code: Anatomy of a Misfeature
#10I think this is a good feature, but should be gated behind a toggle that is off by default, and designed to be enabled per session via prompt.
There are situations when I want Claude to start working on something just as I'm about to head to bed or otherwise step away. It's kind of annoying to come back only to find that Claude worked for just 5 minutes and then decided to pause and ask a question.
That said, I think certain types of questions should not be automatable. Maybe it's already built that way, but I wouldn't want Claude to go with its recommended direction for anything related to operations like deletions, changing external systems, etc. Basically, things that cannot be undone should be a hard-block and wait for user input always.