Hacker News new | ask | show | jobs
by soulofmischief 1100 days ago
Breaking peers into groups and letting them compete on wargames is also a fun exercise. Not sure how this will be impacted by LLM-powered coding software, however.
1 comments

I put the second puzzle into ChatGPT. It makes an extremely stupid mistake but gets lucky.

GPT gets JavaScript numerical semantics utterly wrong but the only non-integer operation is a red herring: "the result [of 14/3] is approximately 4.6667, but JavaScript will store it as 4 since we are not using floating-point numbers"

Is this GPT 3.5, or GPT 4?
3.5
You should try with 4 and compare. 4 is leagues better.
I've yet to be wowed by anything from gpt 3.5 I've gotten myself or 4 I've seen others post, so I'm not gonna buy it.
Doesn't this strike you as an anti-scientific, close-minded / willfully ignorant attitude?

Why not just discover for yourself? I think you would do well to have your own opinions instead of relying on others.