Hacker News Reader

I agree with the premise that LLMs reward experstise, but people without expertise can very eaily learn to prompt correctly and get to a result that is very good. I remember somebody proved a mathematical conjecture by just asking 'keep going' in plain english without a mathematics background.

View on HN

But then what's the point of the proof? I guess it's cool that it's possible, but given enough tokens, you could take someone who's never written a line of code and have them prompt AI to turn their vibe-coded meal prep app into a highly available distributed system with multi-region failover and immutable audit logs.

They would probably get something that checks those boxes in one way or another, but what does it do for them?

Reply on news.ycombinator.com