Hacker News Reader

I guess it's those two same groups arguing about vibe coding. How many of group 1 say LLMs are too low quality when they really mean that it's diminishing their love of coding? And how many of group 2 say LLMs are the best thing ever when they really mean that they are diminishing their pain of coding?

I'm a hard group 1, and I don't really mind if LLMs take my job, just please don't take my passion.

View on HN

I’m in group 1 but I do find LLMs to be helpful. I just tend to comb through their output and fix a bunch of issues. Maybe it’s not that much faster that way but it gets over the activation energy of starting a new project/module/ticket.

I do find that they’re pretty much only useful when I already know how I’m going to complete a task. If I can describe the implementation at the stack trace level I’ll do fine with AI. If I’m even a little lost the AI is a total crapshoot.

Reply on news.ycombinator.com