Comment by AndrewKemendo | Hacker News Reader

Comment by AndrewKemendo | Hacker News Reader

Parent Full thread

> I’ll bet most of the people that can really do it have a hard time intuitively navigating real social interactions

Bingo. Hi that’s me.

I’ve been trying to teach people how to use LLMs effectively not just dump shit in them but actually talk to them like you would expect a computer to understand and it totally breaks peoples brains

I’m quite successful in helping people get somewhere usable that they weren’t…but to get to the point of fluency with computing systems, and I would argue this is prior to LLMs as well, where you can actually get what you want more reliably out of a computing interaction than you can with a human interaction, is an entirely different way of thinking

That mode of thinking is just generally not accessible to the vast majority of humans. Not because there’s something wrong with them

but it takes somebody who can hold both extremely large scale problems and very very granular specific implementation problems in your head all at once and that is a rare skill.

> it takes somebody who can hold both extremely large scale problems and very very granular specific implementation problems in your head all at once

This describes the entire software engineering profession to me.

We have come up with all sorts of devices to make this go more smoothly, or to enable us to focus on specific sub-parts as long as possible.

That said, at some point (both in design and integration), you need vision and attention to detail to make progress. The skill seems learnable to me, but watching others struggle sometimes makes me wonder.

Almost nobody has a fully formed idea going into any project or product

That’s the first thing that people need to understand is that this idea of some platonic product or project or tool kit or framework or library or whatever just doesn’t exist and it’s never going to exist

Do you have a specific discreet finite problem that you need to solve so you solve that and if you do it in a certain way you can solve other problems with that same solution sometimes you don’t need it to do anything more than you’re one thing and so that’s all you built but maybe you want to do more than just one thing and so you build it so that has the capability to do it

So yes fully concur it’s the synthesis of attention to detail and large scale

it’s all of the above

Do you use skills like superpowers and spec-kit in your teachings ?

Not the original commenter, but I feel pretty strongly that frameworks for software review loops are at best training wheels for people who haven't yet developed the right understanding. I don't use any sort of complex skills framework, I just tell the AI what I want while leaving reasonable Claude-sized gaps to fill in, and my results are usually better and often faster than people who get lost in framework management. Perhaps they're more useful for pure greenfield development, but for most software developers who are working on existing systems I have not seen a strong use case for them.

There's one guy I know who constantly has problems with Claude going off-script, and every time I dig in, it's clear that the poor thing is so overloaded with instructions and skill lists that it can't figure out what he actually wants it to do.

The frameworks-and-tools make for good blog fodder too, as they are quite applicable across a range of areas, so many readers will find something that resonates with them, and claude-code-is-pretty-good-these-days is a less blogworthy topic.

No, I don’t know what those are. (Looked them up and I don’t teach every possible handler, but I teach people how to do structured inputs etc..)

I teach TDD philosophy as well as conways law, parnas hiding etc…without using those terms

So things like problem decomposition into tractable chunks minimum viable product, prototyping, how do you iterate, write the smallest possible test… you know things like this which are just taking incremental work and then iterating on it

It’s basically everything I’ve learned about building stuff since 1997

**Interestingly I thought prompt engineering was going to be a fad but it’s turned into a whole ass new discipline which makes less sense as more robust toolchains come into play and models handle the context interpretation better

Take it as you may but I got good results out of those. I would suggest that you take task like porting a code from c++ to go or equivalent complex task and use those skills along with your traditional knowledge of what you expect from a port and see how those skills do. Just annecdote from my side. You can do experimentation on your side.

Follow these channels or videos for better understanding of skills and how they are using it.

https://www.youtube.com/@mattpocockuk

https://www.youtube.com/@EricWTech

https://www.youtube.com/watch?v=eRS3CmvrOvA

That’s too specific to claude and tooling to last

All this stuff is going to be obsolete in like 6 months

Reply on news.ycombinator.com