The conversation

Lessons learnedExperience excerpt · English

Those are crashes that I found hard to fix because even though by human standard I'm both expert …

… Those are crashes that I found hard to fix because even though by human standard I'm both expert developer and expert Windows API developer. But I'm not an autistic machine that can just connect the dots between how every windows api works and how it ties to the callstack and information from the log, in under a minute.

Original discussionWe Rewrote JSONata with AI in a Day, Saved $500K/Year256 source comments · at import
2

What was this responding to?

Parent context · original excerpt

SA

They’ll be forced to work on it when then the bugs in the new system are uncovered. If the system is simple enough someone might take enough time to understand and verify the test suite to the point where they can keep adding regression tests to it and maybe mostly call it done. They probably won’t do this though (based on the situation the company was in in the first place) and people will have Claude fix it and write tests that no one verified. And in a while the test suite will be so full tests that reimplement the code instead of testing it that it will be mostly useless. Then someone else will come in and vibe code a replacement that won’t have the bugs the current system does but will have a whole new set. And the cycle will continue. The same cycle that I’ve seen in the bottom 80% of companies I’ve worked for, just faster.

Full original

Community replies 0

No community replies yet. Add your perspective.

Replies from the source 2

Direct replies available in this import. Original-language excerpts.

HP

That fix is just the same code from earlier in that function pasted in again after another asynchronous procedure. I feel like you’re probably just a worse engineer than you think you are if you needed Claude for this.

Full original
ZA

Fixing a bug is in the wheelhouse of AI to the extent that the fix can be verified — since there is a clear objective function. The real question is whether there are unintended side effects (e.g., new bugs that get introduced) or whether the test cases are comprehensive enough to determine whether the fix worked.

Full original
Continue on Hacker News

Respect different perspectives. Share concrete experiences.

Sign in to post, reply, repost, and quote.