←back to thread

466 points 0x63_Problems | 1 comments | | HN request time: 0.232s | source
Show context
dcchambers ◴[] No.42138389[source]
LLM code gen tools are really freaking good...at making the exact same react boilerplate app that everyone else has.

The moment you need to do something novel or complicated they choke up.

This is why I'm not very confident that tools like Vercel's v0 (https://v0.dev/) are useful for more than just playing around. It seems very impressive at first glance - but it's a mile wide and only an inch deep.

replies(2): >>42138440 #>>42138881 #
holoduke ◴[] No.42138440[source]
If can you can create boilerplate code, logging, documentation, common algorithms by AI it saves you a lot of time which you can use on your specialized stuff. I am convinced that you can make yourself x2 by using an AI. Just use it in the proper way.
replies(6): >>42138509 #>>42138590 #>>42139129 #>>42139261 #>>42140602 #>>42144895 #
1. xarope ◴[] No.42144895[source]
I hate to say this, but you probably can only achieve x2 using AI on the "easy" parts of your work. Going by the 80/20 rule:

  - 80% of your work is easy, and is accomplished in 20% of the time
  - 20% of your work is hard, and takes 80% of the time
If you believe AI can x2 that easy 80% of your work, you have only managed to reduce that 20% to 10%. Someone else can work out that x improvement (1.11?), but it's nowhere near x2.