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

121–130 of 133 posts

Re: Claude Code: Anatomy of a Misfeature

#121

Post by alansaber »

overgard wrote: post #31

One of the things I'm baffled about with Claude code is it seems like it setup a really chunky VM on my computer, and yet by default it doesn't seem to sandbox anything. Also the newer models seem really aggressive about modifying your computer. Yesterday Claude started rewriting system files on my linux machine (user accessible, but still way outside the scope of what I asked.) This wasn't me asking it to debug my m…

Claude code as a harness makes all kinds of weird design decisions, you are probably better off long term with opencode.

Re: Claude Code: Anatomy of a Misfeature

#122

Post by mikelward »

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…

Please stop it asking stale questions repeatedly on the Android app.

Re: Claude Code: Anatomy of a Misfeature

#123

Post by prmph »

cube00 wrote: post #86
trq_ wrote: post #82

Earlier quoted context omitted.

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 i…

I don't know, this is a company that is pushing the narrative of software engineers becoming obsolete. Why do you think they would have respect for Software Engineering processes. As few as they are concerned, a few coders working in isolation with Claude Code is all that you need. (pun unintended)

Re: Claude Code: Anatomy of a Misfeature

#124

Post by prmph »

grim_io wrote: post #103
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…

Not the person you asked. I expect the person responsible for Claude Code to explain the reason this direction was chosen. It is ridiculous to expect individual contributors to do so. Where is the leadership? Can individual contributors decide to significantly alter the workflow of millions of customers? Were any customers consulted at all?

Isn't Anthropic anti software engineering? This state of affairs is exactly what you should expect.

Re: Claude Code: Anatomy of a Misfeature

#125

Post by inigyou »

cute_boi wrote: post #116
inigyou wrote: post #99

Earlier quoted context omitted.

Can't you just ask Claude to decompile it?

It isn’t very smart to recover the code, and Anthropic will ban you because, apparently, decompiling code or training a model constitutes cybercrime, according to Dario and his lackeys.

Ask GLM-5.2 to decompile it

Re: Claude Code: Anatomy of a Misfeature

#126

Post by dymk »

inigyou wrote: post #101
oalders wrote: post #46

Earlier quoted context omitted.

>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…

The article was obviously written by an LLM, it's obviously from the overall structure as well as individual sentences. Maybe you've been exposed to so much LLM text that you write identically to one, in which case, yikes!

The parts outside of the “Claude wrote this” guards seem plausibly written by a human, it’s just that 70% of the article is in the “Claude wrote this” guard.

Re: Claude Code: Anatomy of a Misfeature

#127

Post by esalman »

cadamsdotcom wrote: post #97
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…

Hi Thariq, Chris from ApprovIQ here. We depend on Claude Code to ship. It's our most crucial tool. But we feel an asymmetry. We feel it's not an important to Anthropic as it is to us. We feel the systems by which PRs ship on your side need serious inspection. Claude Code is career-level important not just to us but to a lot of people. So actually, your post and claim of individual accountability gives me less confide…

I think you're vastly overestimating Anthropic.

After they switched tooling from Microsoft to Anthropic at work, I switched to Gemma 4 and Opencode. I've been in this industry for two decades now, I think I understand the risk of putting career level importance on their tooling.

Re: Claude Code: Anatomy of a Misfeature

#128

Post by DanielHB »

alansaber wrote: post #119
DanielHB wrote: post #12

As soon as tokens stop being subsidized I would not trust any harness made by a company that also charges for the compute. Right now the interests align, but as soon as more tokens -> more profit (instead of more revenue and more losses) the perverse incentives will be too big to avoid. It seems inevitable that open source harnesses will win. These companies would do better to just open source their harnesses.

Not that I disagree but I can imagine it's easy enough to ship implicit token increase (ratchet up the COT settings) on then backend

Good point, but it could easily happen from both sides. The harness can just be default-tuned to think longer and harder on problems, or have dark UI patterns so the user _chooses_ the more expensive option even though the less expensive is available.

It just feels your own harness tuning for more token use protects these companies from audits and litigation. I mean this is exactly what is going on with this new feature.

Re: Claude Code: Anatomy of a Misfeature

#129

Post by dang »

Lomlioto wrote: post #3

Depends 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.

We've banned this account for repeatedly breaking the site guidelines. (I'm not talking about this comment - I'm just replying to your most recent one.)

If you want to post on HN, we need you to review and follow the rules at https://news.ycombinator.com/newsguidelines.html. You've already broken them badly and often, including with many personal attacks. That's not allowed here.

Post reply on HN