Hacker News Reader

Comment by jvanderbot | Hacker News Reader

Buried deep is this gem:

    I tried feeding a lot of this into various Als (Kagi gives you access to a few with a nice interface) and I found that they mostly were stupid in ways that made me think.

Perfect summary of why AI is useful for rubber ducking. Doing this with a co-worker you always get some questions that are a few layers too shallow for what you need (because they haven't been thinking about it more than a few minutes), but it always makes you think and really helps.

View on HN

Even when the duck doesn't answer at all it still often works.

I worked next to another engineer in the early eighties who was working on a different project. At tea break time we got into the habit of sitting opposite each other and explaining the problems we were having. Neither of us put much, if any, effort into trying to solve the other's problems because it often turned out that simply attempting to formulate the problem in a way that would make sense to the other party was enough to reveal the answer or at least a promising idea to try.

This. Previous cow-orker of mine that was doing remote-only like 10+ years ago at some other company got an actual yellow rubber duck sent to him together with his company laptop when he joined.

I also like to do this when debugging. I'll just write out whatever my current hypotheses are about what the bug is and I adjust as I go, as I disprove or make them more precise. I would usually just do it right on the ticket. It both helps because it provides the "rubber duck" and in the end I just submit the comment and I have a root cause analysis right there.

Unfortunately it's quite rare to see this from anyone and asking them to provide a root cause analysis is usually fraught with peril. I don't quite get why. It's been working awesomely.

And like OP says, AI hasn't made it better in the sense that not everyone can use AI (or cow-orkers) in that way. They just believe what the AI tells them and they literally won't reverse engineer that protocol in 24h ;)

But the very next sentence is the important bit:

> A few times I thought they had "cracked the case" but actually they just made me waste time.

Despite trying various models and services for years now, I've come to the conclusion that the current iteration of AI services hurts more than it helps. I spend more time prompting, reading pages of babble, and trying to find signal in the noise that I would just chilling out and thinking through the problem.

The technology is neat but not productive.

Reply on news.ycombinator.com