Casey Liss

And the biggest challenge to using these tools is not...

installing the software, it's not paying for the 20 or 100 bucks a month.

The biggest challenge for existing professionals in the field like us to use these tools is that we won't think of what to ask them to do.

That's the hardest part.

We need to think of things to try to assign them.

Young people won't have this problem.

As young people come into the industry, they're going to have grown up with these tools.

They won't have the preconceived notions of where the walls are that we have.

They'll just try a bunch of stuff, and a lot of it will work.

That's the challenge for people like us, like us elder programmers, is that we need to jump into this world and start getting ideas for what to have them do.

By the way, if you want something that can generate a bunch of ideas for you for free, LLMs are really good for that.

So you can literally go to ChatGPT or Gemini or Cloud and you can say, give me 20 ideas for what I can have, Cloud Code or Codex or whatever, what I can have it do in my existing code base or a new code base that I am not thinking of.

You can literally have it tell you, because you know what AI is really good for?

Brainstorming.

Because AI is a BS generator and that's what brainstorming is, is generating BS.

So you can have it tell you how to use it.

And you can then at that point say,

Eh, these don't sound very good.

Give me 50 more and it will happily give you 50 more.

And you can keep doing that because it's not human.