Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

    > …I have experience AI’s deleting
    > things they shouldn’t but not since
    > like, the gpt4 days.…
One blogger posted this [1] only yesterday about what Anthropic's latest and greatest did…

———

…I pointed Opus 4.6 at a 60K line Go microservice I had vibe coded over the past few months, gave it some refactoring principles, and let it run unsupervised…

What went wrong #

At some point in the code, we re-fetch some database records immediately before doing a write to avoid updating from stale data. It decided those calls were unnecessary and _removed them_…

———

[1] https://g2ww.short.gy/ClaudesLaw



Running it entirely unsupervised with “some refactoring principles” is the exact recipe for such a disaster, which supports my point.

That said, this is a very different kind of mistake to make compared to overwriting a file and then insisting it didn’t do that. Any modern model with reasoning would check the git history immediately if you mentioned this had happened, if it had somehow even made the mistake in the first place, but I digress.


    > …this is a very different kind
    > of mistake to make compared
    > to overwriting a file…

Both of my quotes are about some automaton deleting some thing that some human didn't want deleted.

    > …but I digress…
Digressing to what the thing is that got deleted when it shouldn't have, is splitting hairs.

    > …which supports my point…
My point is that believing the latest and greatest version of any piece of software from any brand to be immune to Murphy's Law, seems pretty naïve.


> seems pretty naive

I had cereal for breakfast this morning

> is splitting hairs

I’m a chocolate ice cream guy myself, over strawberry that is.

Sorry, just wanted to join the “quote random parts of a comment and then state completely unrelated statements for unknown reasons” club.




Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: