Hacker News Reader

AI builds like 95% for me than i play around with it for a bit for the last 5%.

I'm still a lot faster for certain things with AI but its weird. Instead of just being annoyed about some weird bug, i'm annoyed about an LLM which can do everything and then falls over itself on weird issues.

It feels weird true but it still also relevant faster?

View on HN

I never liked telling people what to do or watching people do something. Using AI is exclusively like telling someone to do something who is either super smart or dumb as a brick and you never know which persona you will. The only thing you can be sure of is that it will produce whatever it produces very fast with 100% confidence. Also I care for code style, consistency and overall maintainability because I don't want to be locked into using LLMs and I can only really do that when I proof read everything. I don't want a huge project that will take a full rewrite for a human to understand it.

Even worse is having to telling people to do stuff who then turn around and use AI to do a poor job without the human rationalizing the problem or result.

Reply on news.ycombinator.com