Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Claude Code: Anatomy of a Misfeature

olafalders.com

Post reply on HN
Print view View original

81–90 of 133 posts

Re: Claude Code: Anatomy of a Misfeature

#81

Post by leobuskin »

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…

Is there a way to turn options-based AskUserQuestion off? I couldn't find it at all, and the "options" selector is the most annoying thing in CC for me, plain-text is the only way, everything else is distracting. I know, I can use `n` (sometimes) or cancel it, but both bring more pain that just regular communication (cancellation does one more chat step + requires an extra action, same with `n`)

Re: Claude Code: Anatomy of a Misfeature

#82

Post by trq_ »

Jcampuzano2 wrote: post #79
brabel wrote: post #69

Earlier quoted context omitted.

> 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 ev…

> 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. In a sense yes, I think it is actually reasonable to complain that the answer is too human/individualized here because it likely wasn't this individual human who made this decision, but he's making it seem like it is so that we are less likely to blame the company as a whole.…

I did make the decision, and shipped the PR.

Re: Claude Code: Anatomy of a Misfeature

#83

Post by trq_ »

demosthanos wrote: post #55
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…

For what it's worth, I totally understand the motivating use case here. There were absolutely times where I walked away from what I was hoping would be an hours-long project that would run to completion and came back to find that Claude had asked me a question early on and I'd missed out on a large amount of implementation time. So you were not imagining that the use case is real! It's also worth adding that I really…

Thank you! Appreciate it. I love wrestling with the problem of making sure Claude is in the loop with you in the way you want. More to come!

Re: Claude Code: Anatomy of a Misfeature

#84

Post by Jcampuzano2 »

trq_ wrote: post #82
Jcampuzano2 wrote: post #79

Earlier quoted context omitted.

> 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. In a sense yes, I think it is actually reasonable to complain that the answer is too human/individualized here because it likely wasn't this individual human who made this decision, but he's making it seem like it is so that we are less likely to blame the company as a whole.…

I did make the decision, and shipped the PR.

Okay I stand corrected then.

Seems strange for a company of your size to have one person push changes that should have easily caught this edge case then. Seems like a change even a small handful of people could have reasonably thought up this side effect of.

Re: Claude Code: Anatomy of a Misfeature

#85

Post by hombre_fatal »

trq_ wrote: post #64
lubujackson wrote: post #61

Earlier quoted context omitted.

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

It would be nice to use automode in planning mode.

Right now planning mode (e.g. I want claude to do all the planning necessary to create a robust plan file) still prompts you with trivial things, especially one-off things you wouldn't care to add to your whitelist. Yet if you switch into automode, then it's not in planning mode anymore.

Repro:

1. Prompt "Implement a hello world in C" in planning mode

2. Switch to automode

3. It writes hello.c instead of a plan file

Re: Claude Code: Anatomy of a Misfeature

#86

Post by cube00 »

trq_ wrote: post #82
Jcampuzano2 wrote: post #79

Earlier quoted context omitted.

> 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. In a sense yes, I think it is actually reasonable to complain that the answer is too human/individualized here because it likely wasn't this individual human who made this decision, but he's making it seem like it is so that we are less likely to blame the company as a whole.…

I did make the decision, and shipped the PR.

There has to be a second PR approver. There's no way a company as large this can allow an individual the ability to push to production without a secondary person involved.

When there's at least two people involved you can then start to look at more systematic factors that go beyond any single human mistake.

When both the submitter and approver miss that there's no changelog entry for a PR does that mean a checklist is needed? Should the changelog be automated with the commit message which can be improved for external consumption?

I'd find it very hard to believe that this high profile change just happened to be the only change missing from the changelog.

Bugs are always going to happen but housekeeping like writing something to a changelog when a commit is merged can be quality assured.

Re: Claude Code: Anatomy of a Misfeature

#87

Post by cute_boi »

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…

All these words don't mean anything when you got no intention to open source claude code. Even grok cli is open-sourced.

Re: Claude Code: Anatomy of a Misfeature

#88

Post by rao-v »

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.

Codex legit does a great job of this with it's auto-review feature. Does a good job of understanding what permissions I'm implicitly giving with the request, and where it needs to actually ask me to grant permission.

Re: Claude Code: Anatomy of a Misfeature

#89

Post by csomar »

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.

This is by design. Anthropic treat users as paying workers (how futuristic!). Their end game is to replace software developers (and it's not like they are trying to hide that?)

Re: Claude Code: Anatomy of a Misfeature

#90

Post by cadamsdotcom »

trq_ wrote: post #82
Jcampuzano2 wrote: post #79

Earlier quoted context omitted.

> 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. In a sense yes, I think it is actually reasonable to complain that the answer is too human/individualized here because it likely wasn't this individual human who made this decision, but he's making it seem like it is so that we are less likely to blame the company as a whole.…

I did make the decision, and shipped the PR.

Unfortunately this is a sign that the systems by which PRs are shipped need serious inspection.

For example in incident management, the industry settled on blameless postmortems. Blame is pointed at the systems which allowed incidents to occur, never the human(s) who triggered the incident. "Just don't make that mistake again" simply doesn't work. Humans make mistakes!

There are too many stakeholders in a product this large, even if every one of them wishes it were not so. The systems by which this PR shipped need serious inspection.

Post reply on HN