Potential issues in curl found using AI assisted tools

Post by zdragnar » Thu, Oct 02, 2025, 10:18 PM UTC

dylan604 wrote: post #90

Sharlin wrote: post #32

Earlier quoted context omitted.

This is a point I see discussed surprisingly little. Given that many (most?) programmers like designing and writing code (excluding boilerplate), and not particularly enjoy reviewing code, it certainly feels backwards to make the AI write the code and relegate the programmer to reviewing it. (I know, of course, that the whole thing is being sold to stakeholders as "LoC machine goes brrrr" – code review? what's that?)

To me, it's the natural result of gaining popularity that enough people have started to use after the hype train rolled through and are now giving honest feedback. Real honest feedback can feel like a slap in the face when all you have had is overwhelming positive feedback from those aboard the hype train. The writing has been on the wall with so called hallucinations where LLMs just make stuff up that the hype was w…

Post by dylan604 » Thu, Oct 02, 2025, 10:56 PM UTC

zdragnar wrote: post #101

dylan604 wrote: post #90

Earlier quoted context omitted.

To me, it's the natural result of gaining popularity that enough people have started to use after the hype train rolled through and are now giving honest feedback. Real honest feedback can feel like a slap in the face when all you have had is overwhelming positive feedback from those aboard the hype train. The writing has been on the wall with so called hallucinations where LLMs just make stuff up that the hype was w…

I saw an article today from the BBC where travellers are using LLMs to plan their vacations and getting into trouble going places (sometimes dangerously remote ones) to visit landmarks that don't even exist: https://www.bbc.com/travel/article/20250926-the-perils-of-le... I'm mildly bearish on the human capacity to learn from its mistakes and have a feeling in my gut that we've taken a massive step backwards as civili…

Post by alickz » Thu, Oct 02, 2025, 11:13 PM UTC

diggan wrote: post #56

dingnuts wrote: post #50

Earlier quoted context omitted.

I'm still faster than the cheap bots. The creative part for me includes both the implementation and the design, because the implementation also matters. The bots get in the way. Maybe I would be faster if I paid for Claude Code. It's too expensive to evaluate. If you like your expensive AI autocomplete, fine. But I have not seen any demonstrable and maintainable productivity gains from it, and I find understanding my…

> The creative part for me includes both the implementation and the design The implementations LLMs end up writing are predicable, because my design locks down what it needs to do. I basically know exactly what they'll end up doing, and how, but it types faster than I do, that's why I hand it off while I go on to think about the next design iteration. I currently send every single prompt to Claude, Codex, Qwen and Ge…

Post by alickz » Thu, Oct 02, 2025, 11:25 PM UTC

CharlesW wrote: post #43

flohofwoe wrote: post #4

This is exactly what I'd want from an 'AI coding companion'. Don't write or fix the code for me (thanks but I can manage that on my own with much less hassle), but instead tell me which places in the code look suspicious and where I need to have a closer look. When I ask Claude to find bugs in my 20kloc C library it more or less just splits the file(s) into smaller chunks and greps for specific code patterns and in t…

> When I ask Claude to find bugs in my 20kloc C library it more or less just splits the file(s) into smaller chunks and greps for specific code patterns and in the end just gives me a list of my own FIXME comments (lol), which tbh is quite underwhelming - a simple bash script could do that too. Here's a technique that often works well for me: When you get unexpectedly poor results, ask the LLM what it thinks an effec…

Post by blibble » Fri, Oct 03, 2025, 12:18 AM UTC

dylan604 wrote: post #103

zdragnar wrote: post #101

Earlier quoted context omitted.

I saw an article today from the BBC where travellers are using LLMs to plan their vacations and getting into trouble going places (sometimes dangerously remote ones) to visit landmarks that don't even exist: https://www.bbc.com/travel/article/20250926-the-perils-of-le... I'm mildly bearish on the human capacity to learn from its mistakes and have a feeling in my gut that we've taken a massive step backwards as civili…

I could almost understand a lawyer working late the night before a brief is due and just run out of time to review the output of the LLM. How do you not look up travel destinations before heading out? That's just something I can't wrap my head around in any way of trying to be kind and seeing the other side of something