I see this sentiment pretty regularly, and I don’t get it. Variable rewards is not sufficient to establish that it is “ basically gambling”.

Everything in life is variable reward. You invite a friend over, they might accept or they might not. Drive to work, traffic might be good or might be bad. You ask a colleague to finish a task, they might do it or might not or might do a good job or might not.

Everything is variable reward. Is everything gambling?

This is why I also suspect them to waste tokens on purpose.

Literally putting tokens into a machine and hoping profit comes out. Amazing.

Programming before AI was always variable reward. It was a gamble against your own time and patience. Maybe I'd waste hours down the wrong rabbit holes trying to find a library that worked for my use case. Maybe I'd waste a day trying to get an API to do something it turned out it couldn't do. Maybe I'd have to redo my entire approach because of some factor I hadn't considered. Something I wrote could have worked on the first try or I could have had to spend the day chasing logic errors (or multiple days chasing memory errors if it was C or C++). Maybe I would just get bored of the project, especially if I realized there were 20 layers of yaks I needed to shave first, and Visual Studio got stuck updating again, and before I could even start actually coding I had to spend the entire evening on an exhausting merge conflict. My entire weekend could be gone with nothing to actually show for it.

I got so sick of all this at some point that I slowly stopped doing anything that wasn't my job. But then AI got better and better and I realized it was the ultimate unblocker. When that dreaded malaise started creeping in signaling it was a project's end because I didn't want to waste any more of my life dealing with bullshit orthogonal to what I was trying to do, I'd give it to the AI. It felt like a miracle the first time this worked, and it still does. If we were previously equipped with shovels to dig through bullshit, we now have a fully automated Bagger 288.

The reward schedule now isn't variable anymore; the chance that I finish something in a good state is 100%. I can focus on the parts I actually enjoy - architecting the broader system, making the parts mesh together in a sensible way that's easy to work with and has some mathematical elegance to it, hand coding the bits I want to be really specific about (but now without the endless frustration of bugfixing or import errors and edgecases being immediately discovered, thanks to the AI).

Modern LLM services are engineer's pipe dream that was heavily shaped by the shadiest product management dark patterns you can find: applying gambling-style engagement tactics, exploiting cognitive biases, exploiting users' lack of technical understanding to inflate product expectations, using fear mongering in external and investor communications. And that's not even a complete list.

Which also explains why response speed is so important.

Gambling but with positive expected value, yes.

Is it gambling if I'm beating the house?

Something regulators should look at. They don't deliver consistent compute, yet charge consistent money. In my opinion that's fraud.

People say this, but I've never seen it. AI has been very consistent in its rewards for me.