Re:I asked ChatGPT to write the code to print "Hello, world ...
by Vingdoloras on Tuesday March 26, 2024 @04:58AM
(#39825591)
I forgot what people were calling it but this is almost exactly the same idea as that trend where you ask ChatGPT to generate pictures, continuously asking for "more" of some aspect of the picture (make this dish more spicy, etc), only hidden by the fact that instead of simply asking it to make the code more complex, they're naming specific (but in the end, arbitrary) steps of what ChatGPT would still interpret as escalation.
Re:I asked ChatGPT to write the code to print "Hello, world ...
by karmakaze on Tuesday March 26, 2024 @09:57AM
(#39827877)
That would be awesome if ChatGPT picked up on the prompts as cues to generate a joke. Sounds fine for generation of entertainment content, but less so for anything critical.
So to round-out the joke, ask it how a 'galaxy brain' would write it, and we should end up at console.log(message) again.
This is a sequence of prompts in a single context which is “pre biasing” the LLM to respond the way you want it to.
Many such “emergent behaviours” are from the asker, not the LLM.
When you look in the mirror, you only see yourself.
> In the final exercise of this experiment, I challenged ChatGPT to step back, assess the code's objectives, and propose a better solution. The attempt was unsuccessful at first, as it continued to tweak the existing program and preserve the "existing architecture." Only when I instructed it to envision starting from scratch did it offer a new solution, as follows:
Surprise.
Naive usage.