Claude Code: Anatomy of a Misfeature • Hacker News Board

Re: Claude Code: Anatomy of a Misfeature

#61

Post by lubujackson » Fri, Jul 17, 2026, 4:54 PM UTC

trq_ wrote: post #47

Hi everyone, It's Thariq from the Claude Code team here. This was my change! I made the AskUserQuestion tool so am generally in charge of maintaining it. First, overall wanted to apologize and agree that this did not meet our bar and does not represent how we plan to ship on Claude Code. To give you a motivating sense, as the models get more powerful, usage patterns start to change. I'd gotten a lot of feedback that…

Instead of one-off fixes Claude should have a much richer interface to configure between "ask approval every time" and "YOLO dangerously". I should be able to trivially set "run this task until completed" and have settings like: don't consult the web, don't touch files outside of the codebase, don't delete anything, etc. They don't have to be perfect, just better than the all or nothing system we have now.

Re: Claude Code: Anatomy of a Misfeature

#62

Post by wlamartin » Fri, Jul 17, 2026, 4:55 PM UTC

neerajsi wrote: post #54

ryandvm wrote: post #51

Earlier quoted context omitted.

Yes! This is awful. CC should not have copy/paste behavior that is different from literally every other CLI app.

I wonder if it's the same behavior as copilot cli. I dug into it when I got annoyed and found that there's a fundamental tension between rendering the cell based UI and supporting the terminal's native copy paste. At least on copilot cli there were extra zero width characters being copied.

My memory is that once you begin using the alternate screen, you need to turn on mouse reporting, and then you lose native copy. Different terminal emulators also act totally differently when in this state.

Re: Claude Code: Anatomy of a Misfeature

#63

Post by chaboud » Fri, Jul 17, 2026, 4:56 PM UTC

trq_ wrote: post #47

Hi everyone, It's Thariq from the Claude Code team here. This was my change! I made the AskUserQuestion tool so am generally in charge of maintaining it. First, overall wanted to apologize and agree that this did not meet our bar and does not represent how we plan to ship on Claude Code. To give you a motivating sense, as the models get more powerful, usage patterns start to change. I'd gotten a lot of feedback that…

(Edit: BTW, if you haven't, read Nudge by Thaler and Sunstein. It's a somewhat long-winded exploration on choice architectures, but you're neck deep in that space now. I'll give you my copy if you're in SF.)

Thanks for the openness. I got bit by this one and was, frankly, pretty surprised.

The funny thing about user-facing interaction mechanics is that everyone is part of some minority, and everyone comes with their own sense of what "natural" or "obvious" is. With something this impactful, communicated clarity of behavior will important. Your feature is also doing double-duty, serving as a last net against prompt-injection attacks by giving the user the final say.

(Also, BTW, folks outside of Anthropic are unlikely to be as tooled-up for long-running unsupervised Claude jaunts as you guys. The cost of wild success is wide adoption.)

One thing I'll suggest is that the mechanics of permissions and asking are presently pretty hacker/nerd friendly but simultaneously too-scary and not-scary-enough for non-coders.

Examples:

- Wild-cards on always approve is awesome, but, with prefixes like timeout and nohup, the "thing" that is getting done is buried and largely unexplained to the user.

- Auto is actually kind of a sweet spot (sometimes goes off into the weeds), but the designers and PM's I've been working with might as well YOLO. They have no idea if they're breaking things, but they gravitate between plan and auto mode.

- Fewer permission prompts is great, but it comes after a user has slogged through generation of a data-set to work against, like battle scars for paper cuts. It's the thermostat problem. The signal comes when the user is uncomfortable. And it's a way to learn me, but not me now.

I've had good fortune with Opus 4.8 and Fable just telling the system what phase of my life it's in. Things like "I'm going to go make dinner... Go profile the matrix or configurations and build the dataset for the next two hours while I'm away" have a pretty good hit rate. On the flip side "keep me in the loop and bring me your results before making structural changes" also articulates well with Fable. It will tread more carefully.

And these approaches are the ones we'd use with someone transitioning from SDE1 to SDE2. A little more autonomy, and the grounding in the bigger picture. Can we eventually translate to perfectly judging what the user wants in the moment based on incomplete signal?

No, but I'm glad you're trying. Keep the interaction model clear to your broad set of users, and we'll come along for the ride.

Re: Claude Code: Anatomy of a Misfeature

#64

Post by trq_ » Fri, Jul 17, 2026, 4:57 PM UTC

lubujackson wrote: post #61

trq_ wrote: post #47

Hi everyone, It's Thariq from the Claude Code team here. This was my change! I made the AskUserQuestion tool so am generally in charge of maintaining it. First, overall wanted to apologize and agree that this did not meet our bar and does not represent how we plan to ship on Claude Code. To give you a motivating sense, as the models get more powerful, usage patterns start to change. I'd gotten a lot of feedback that…

Instead of one-off fixes Claude should have a much richer interface to configure between "ask approval every time" and "YOLO dangerously". I should be able to trivially set "run this task until completed" and have settings like: don't consult the web, don't touch files outside of the codebase, don't delete anything, etc. They don't have to be perfect, just better than the all or nothing system we have now.

automode mostly fixes these things, it runs a classifier on every request that would have required permissions to make sure it matches your request

Re: Claude Code: Anatomy of a Misfeature

#65

Post by fooster » Fri, Jul 17, 2026, 4:58 PM UTC

randysalami wrote: post #59

trq_ wrote: post #47

Hi everyone, It's Thariq from the Claude Code team here. This was my change! I made the AskUserQuestion tool so am generally in charge of maintaining it. First, overall wanted to apologize and agree that this did not meet our bar and does not represent how we plan to ship on Claude Code. To give you a motivating sense, as the models get more powerful, usage patterns start to change. I'd gotten a lot of feedback that…

I read the article but I find this response kind of strange. Am I alone in this? Wanton accountability for a multi-billion dollar cutting edge company… leaves more to be desired from the best? Take Apple or Google or any top tech company of the past at its prime and compare. This kind of behavior then would probably reflect poorly on the institutions behind the tech and not maintain their image of technical brillianc…

It doesn't feel strange to me at all. It feels like a very human response from the person that introduced the change. I great appreciate that, rather than ignoring the problem, or some canned corpspeak response.

Re: Claude Code: Anatomy of a Misfeature

#66

Post by blixt » Fri, Jul 17, 2026, 5:00 PM UTC

oalders wrote: post #46

blixt wrote: post #38

So much attribution to malintent here, but most likely they're trying to build a product with the features that they themselves would use, and from my own experience it's very frustrating to leave a Claude session running and come back to find it did nothing because it got stuck on a question. Furthermore, believing that the only thing saving you from disaster is Claude deciding to ask you a question is not a great c…

>Meanwhile, this article was written by Claude The prose was written by me, with the research being done by Claude and also clearly attributed. I left Claude's research as a series of bullet points so that it would be clear that I'm not passing off an LLM's work as my own, but if anyone wants to dig deeper, they have some starting points to consider. I don't publish prose written by an LLM for the same reason I would…

Then I apologize, it seemed to me you wrote that part, but I guess I was reading Claude output.

Re: Claude Code: Anatomy of a Misfeature

#67

Post by hedgehog » Fri, Jul 17, 2026, 5:00 PM UTC

overgard wrote: post #44

hedgehog wrote: post #13

Earlier quoted context omitted.

It's what some more experienced users want and the companies are following the well-trod path of optimizing heavily for power users at the expense of complexity, only now it's gotten easier to add absurd amount of code to a project. Not necessarily to make it work right. Personally I have some tasks where sessions between one and five days are typical so I appreciate that it's possible.

Experienced in what dimension? I've been using these tools for about a year and coding for 20+ years, and frankly these long horizon tasks are the OPPOSITE of what I want. I want quick iteration cycles so that it doesn't spend a lot of time and tokens building things I need to throw out. I think the people that mostly want long horizon tasks are: AI labs, because they want you to spend tokens, and vibe coders, who ar…

I don't know about the overall breakdown but in my case longer runs are prototyping, bug hunting, reverse engineering, etc. For example Gnome Remote Desktop didn't work in my configuration due to a combination of hardware and codec bugs and settings. One drive to make it work, another to backport the current upstream packages to Debian stable, restack the patches, and push to my machines. Another sequence of long runs was writing a new client for a closed-source conferencing service I use to allow fixing some particularly irritating bugs. Exploit development has the same shape although that's not something I do personally. From what I've seen the amount of useful hands-off run time is directly related to how clearly it's possible to specify a concrete, verifiable standard by which to judge the outcome. For some tasks that might be days or weeks, for forward engineering on a software product that for me is usually under an hour.

Re: Claude Code: Anatomy of a Misfeature

#68

Post by hombre_fatal » Fri, Jul 17, 2026, 5:02 PM UTC

lubujackson wrote: post #61

trq_ wrote: post #47

Hi everyone, It's Thariq from the Claude Code team here. This was my change! I made the AskUserQuestion tool so am generally in charge of maintaining it. First, overall wanted to apologize and agree that this did not meet our bar and does not represent how we plan to ship on Claude Code. To give you a motivating sense, as the models get more powerful, usage patterns start to change. I'd gotten a lot of feedback that…

Instead of one-off fixes Claude should have a much richer interface to configure between "ask approval every time" and "YOLO dangerously". I should be able to trivially set "run this task until completed" and have settings like: don't consult the web, don't touch files outside of the codebase, don't delete anything, etc. They don't have to be perfect, just better than the all or nothing system we have now.

At least there's an auto-approval mode now that uses another agent to sanity check commands. Before it, the options really were manual vs yolo.

Re: Claude Code: Anatomy of a Misfeature

#69

Post by brabel » Fri, Jul 17, 2026, 5:03 PM UTC

randysalami wrote: post #59

trq_ wrote: post #47

Hi everyone, It's Thariq from the Claude Code team here. This was my change! I made the AskUserQuestion tool so am generally in charge of maintaining it. First, overall wanted to apologize and agree that this did not meet our bar and does not represent how we plan to ship on Claude Code. To give you a motivating sense, as the models get more powerful, usage patterns start to change. I'd gotten a lot of feedback that…

I read the article but I find this response kind of strange. Am I alone in this? Wanton accountability for a multi-billion dollar cutting edge company… leaves more to be desired from the best? Take Apple or Google or any top tech company of the past at its prime and compare. This kind of behavior then would probably reflect poorly on the institutions behind the tech and not maintain their image of technical brillianc…

> it shows weakness in a vulnerable way. It is human. It is not strategic.

Are you complaining that the answer is too human and that a multi billion company should not allow a human who made a mistake to own the mistake in public, being honest about what happened in this case?? Would you prefer complete silence from them like you most certainly would from Google or Apple.

That sounds incredibly sad to me, we don’t even expect humanity from big tech since that’s what we’ve become accustomed to seeing.

fTR both the Anthropic dev response and the blog post seem to believe that a single person can be blamed for something like this, which I wholeheartedly disagree with! Nobody reviews your changes? There’s no QA? Not even an AI checking the release notes match the diff from the previous release?? Blaming a dev for “putting a serious bug in production” sounds really 90’s to me.

Re: Claude Code: Anatomy of a Misfeature

#70

Post by dbbk » Fri, Jul 17, 2026, 5:04 PM UTC

trq_ wrote: post #47

Hi everyone, It's Thariq from the Claude Code team here. This was my change! I made the AskUserQuestion tool so am generally in charge of maintaining it. First, overall wanted to apologize and agree that this did not meet our bar and does not represent how we plan to ship on Claude Code. To give you a motivating sense, as the models get more powerful, usage patterns start to change. I'd gotten a lot of feedback that…

Are you also responsible for AskUserQuestion swallowing the preceding output on Fable? It asks me questions about its response that it never even showed me. It's (and I hate to use the term) unusable.

It is such a shame that Anthropic has no interest in QA, because they have incredible models, and bafflingly broken products. In an alternate universe Claude Code would be 10x better than where it is now...