AI coding is gambling

The gambling metaphor often applied to vibecoding implies that the outcome cannot be fully controlled or influenced, such as a slot machine. Opus 4.5 and beyond show that it not only can be very much can be influenced, but also it can give better results more consistently with the proper checks and balances.

Re: AI coding is gambling

#6

Post by samschooler » Wed, Mar 18, 2026, 6:00 PM UTC

I think there are levels to this.

- One shot or "spray and pray" prompt only vibe coding: gambling.

- Spec driven TDD AI vibe coding: more akin to poker.

- Normal coding (maybe with tab auto complete): eating veggies/work.

Notably though gambling has the massive downside of losing your entire life and life savings. Being in the "vibe coding" bucket's worse case is being insufferable to your friends and family, wasting your time, and spending $200/month on a max plan.

Re: AI coding is gambling

#7

Post by xnx » Wed, Mar 18, 2026, 6:01 PM UTC

...and the payouts are fantastic.

Re: AI coding is gambling

#8

Post by Retr0id » Wed, Mar 18, 2026, 6:03 PM UTC

> But now either the AI can handle it or it can pretend to handle it. Frankly it's pretending both times, but often it's enough to get the result we need.

This has been how I think about it, too. The success rates are going up, but I still view the AI as an adversary that is trying to trick me into thinking it's being useful. Often the act is good enough to be actually useful, too.

Re: AI coding is gambling

#9

Post by Retr0id » Wed, Mar 18, 2026, 6:04 PM UTC

some_random wrote: post #2

How often do you have to win before it's no longer gambling?

I don't know where I'd draw the line personally, but wherever you draw it there's a problem. If you give increasingly more advanced tasks to it, you will eventually cross the line.

Re: AI coding is gambling

#10

Post by simonw » Wed, Mar 18, 2026, 6:06 PM UTC

Assigning work to an intern is gambling: they're inherently non-deterministic and it's a roll of the dice whether the work they do will be good enough or you'll have to give them feedback in order to get to what you need.