Recent AI failures are cracks in the magic

boem@lemmy.world to Technology@lemmy.world – 234 points –
Recent AI failures are cracks in the magic
theintrinsicperspective.com
108

You are viewing a single comment

Trying to make real and good use of AI generative models are cracks in the magic.

It's pretty useful if you know exactly what you want and how to work within it's limitations.

Coworkers around me already use ChatGPT to generate code snippets for Python, Excel VBA, etc. to good success.

Right, it's a tool with quirks, techniques and skills to use just like any other tool. ChatGPT has definitely saved me time and on at least one occasion, kept me from missing a deadline that I probably would have missed if I went about it "the old way" lmao

You mean they're using it to write boilerplate which shouldn't have been written in the first place.

Call it whatever makes you feel happy, it is allowing me to accomplish things much more quickly and easily than working without it does.

Until someone has to maintain it.

That's why I said code "snippets". I don't trust it to give me the entire answer right from the get go, because I acknowledge its limitations and review it before pasting it in. I find it works better if I tell it to generate specific code rather than everything at once.

Plus, we're not working on mission critical server stuff here. Those are code used for data analysis which probably could also be found on Stackoverflow anyway. If it works, it works.

Why? If you know how to incorporate "boilerplate" and modify it correctly into your own code, what difference does it make if its from ChatGPT or Stackoverflow?

Difference to copy and paste from stackoverflow, probably not terribly much. The latter is already bad.

It's as if the young'uns heard the term "10x developer" and decided that not understanding what you're doing is the way to get there.