Comment by anthonyrstevens
4 hours ago
>> LLM technology doesn't work very well for software development
This comment is so obviously false (in my experience) I'm wondering what sort of niche environment you're working in
4 hours ago
>> LLM technology doesn't work very well for software development
This comment is so obviously false (in my experience) I'm wondering what sort of niche environment you're working in
As I mentioned in this thread the other day, it's not worth debating AI skeptics anymore in 2026, with step changes like Fable and Sol. Maybe it was the case in 2025 and before but the field has improved rapidly that it doesn't make sense to listen to people with AI experiences prior to that who haven't touched it since. Does AI make mistakes, sure, but increasingly fewer.
https://news.ycombinator.com/item?id=49051369
> As I mentioned in this thread the other day, it's not worth debating AI skeptics anymore in 2026
This is pretty rude!
My dude. People like you have been making this same claim for literally years now. We've been getting it for every single model that came out ever since 2023. It's never yet been true. Don't act like it's the fault of your interlocutors when they are skeptical of a claim you make, instead pay attention to the fact that you are following up many people who falsely claimed the same thing. It's perfectly rational to be skeptical under those conditions.
Just my personal experience. I'm not really interested in giving up more personal details in this forum, apologies for that.
I'm generally pretty accepting of trust me bro style arguments where we some claims presented without evidence. Especially for AI, sure some model just rm -rf ed your home directy bro sounds bad. It works fine for online discourse.
This is less agreeable. You kind of just made statements without even having claims (even without requirement of evidence or details) to back them up.
This is like the illusion of contribution.
remember, how useful LLMs are is inversely proportional to your skills.
i have yet to have an LLM beat me. i am forced to try regularly so i don't look like an AI anti at a company that is very much SV pilled
I don’t think people like Linus Torvalds or Stephen Wolfram feel like language models beat them, just they’ve managed to find specific cases where flawed brainless workhorses serve their needs.
Like so many things in life, It Depends (tm).
Some developers work better with LLMs in their workflows than others. Some problems are easier for LLMs to generate a reasonable solution for than others. Some folks prompt minimally and see what the vibes bring. Others start with a detailed architecture and implementation plan.
The individual results will depend quite a lot on the person, the problem, and the approach. It's not a guaranteed winning formula for everyone.