Hacker News Reader

Comment by ctoth | Hacker News Reader

Sometimes, you'll just have a really productive session with Claude Code doing a specific thing that maybe you need to do a lot of.

One trick I have gotten some milage out of was this: have Claude Code research Slash commands, then make a slash command to turn the previous conversation into a slash command.

That was cool and great! But then, of course you inevitably will interrupt it and need to do stuff to correct it, or to make a change or "not like that!" or "use this tool" or "think harder before you try that" or "think about the big picture" ... So you do that. And then you ask it to make a command and it figures out you want a /improve-command command.

So now you have primitives to build on!

Here are my current iterations of these commands (not saying they are optimal!)

https://github.com/ctoth/slashcommands/blob/master/make-comm...

https://github.com/ctoth/slashcommands/blob/master/improve-c...

View on HN

I find amazing all the effort that people put trying to program a non deterministic black box. True courage.

Oh do let me tell you how much effort I put into tending my non-deterministic garden or relationships or hell even the contractors I am using to renovate my house!

A few small markdown documents and putting in the time to understand something interesting hardly seems a steep price!

The contractors working on my house sometimes paint a room bright pink for no particular reason.

When I point that out, they profusely apologize and say that of course the walls must be white and wonder why they even got the idea of making them pink in the first place.

Odd, but nice fellows otherwise. It feels like they’re 10x more productive than other contractors.

I asked my contractor to install a door over the back stairs opening outward, came back, and it was installed opening inward. He told me he tried to figure out a way he could do it in-code, but there wasn't one, so that's what he had to do. I was slightly miffed he didn't consult me first, but he did the pragmatic thing.

This actually happened to me Monday.

But sure, humans are deterministic clockwork mechanisms!

Are you now going to tell me how I got a bad contractor? Because that sure would sound a lot like "you're using the model wrong"

The big difference is that when questioned he didn't profusely apologize and immediately get to work undoing it, but instead gave you a reason that was probably causally related to the decision he made and not a retroactive justification made up on the spot.

You're giving people a lot of credit. Often when I ask for justification for stupid decisions I get dumb rationale that makes no sense, or no rationale at all, or something very clearly made up on the spot.

I mean I get your trying to make a joke but a contractors fucking up paint and trying to gaslight you into believing it's the one you signed off on isn't that rare.

Also, they paint the whole room for $2.41! When you add that critical detail the analogy comes into focus.

People aren't excited about AI coding because it's so much better than human coders. They're excited because it's within spitting distance while rounding down to free.

Our brains are non deterministic black box. We just don't like to admit it.

"This system has severe limitations. But we should rely more on it because this other system is also limited."

For several decades we've developed and use computers because they can be very precise and deterministic.

You might also find it amazing that people work with colleagues and give them feedback!

Colleagues take that feedback and improve. It seems a large number of people here seem to find these kind of improvements in other humans useless in the hypothetical case of them leaving but I occasionally look at my mentee's LinkedIn and feel a sense of pride at having contributed. I also feel joy when they appreciate my efforts.

I genuinely don't understand how often people compare AI to junior developers.

Reply on news.ycombinator.com