←back to thread

What to build instead of AI agents

(decodingml.substack.com)
233 points giuliomagnifico | 7 comments | 03 Jul 25 00:02 UTC | HN request time: 0.209s | source | bottom
Show context
mindwok ◴[03 Jul 25 01:06 UTC] No.44450569[source]▶
I'm not yet convinced (though I remain open to the idea) that AI agents are going to be a widely adopted pattern in the way people on LinkedIn suggest.

The way I use AI today is by keeping a pretty tight leash on it, a la Claude Code and Cursor. Not because the models aren't good enough, but because I like to weigh in frequently to provide taste and direction. Giving the AI more agency isn't necessarily desirable, because I want to provide that taste.

Maybe that'll change as I do more and new ergonomics reveal themselves, but right now I don't really want AI that's too agentic. Otherwise, I kind of lose connection to it.

replies(3): >>44450601 #>>44450841 #>>44451530 #
thimabi ◴[03 Jul 25 01:11 UTC] No.44450601[source]▶
Do you think that, over time, knowing how the models behave, simply providing more/better context and instructions can fill this gap of wanting to provide taste and direction to the models’ outputs and actions?

My experience is that, for many workflows, well-done “prompt engineering” is more than enough to make AI models behave more like we’d like without constantly needing us to weight in.

replies(4): >>44450627 #>>44450642 #>>44451992 #>>44452051 #
1. mindwok ◴[03 Jul 25 01:18 UTC] No.44450642[source]▶
I suppose it's possible, although the models would have to have a really nuanced understanding about my tastes and even then it seems doubtful.

If we use a real world analogy, think of someone like an architect designing your house. I'm still going to be heavily involved in the design of my house, regardless of how skilled and tasteful the architect is. It's fundamentally an expression of myself - delegating that basically destroys the point of the exercise. I feel the same for a lot of the stuff I'm building with AI now.

replies(1): >>44450756 #
2. thimabi ◴[03 Jul 25 01:36 UTC] No.44450756[source]▶
Can you share some examples of things you’ve been building with AI?

From your comments, I’d venture a guess that you see your AI-assisted work as a creative endeavor — an expression of your creativity.

I certainly wouldn’t get my hopes up for AI to make innovative jokes, poems and the like. Yet for things that can converge on specific guidelines for matters of taste and preferences, like coding, I’ve been increasingly impressed by how well AI models adapt to our human wishes, even when expressed in ever longer prompts.

replies(2): >>44450860 #>>44450872 #
3. QuadmasterXLII ◴[03 Jul 25 01:51 UTC] No.44450860[source]▶
One example: as a trial, I wanted to work out how frequently an 1400 rated chess player can get a particular opening trap. I intended to check this for all the traps, so it needed to be fast. With a surprising amount of handholding, claude code downloaded the relevant file from lichess. Its method of computing the probability was wrong, so I told it the formula to use and it got the right answer, but incredibly slowly. I asked it to precompute and cache a datas structure for accelerating these queries and it splashed around ineffectually for a long time with sqlite while I made dinner. I came back and clarified that just sorting all the games in the rating range and pickling that list of strings was a fine datastructure, then use binary search to do the probability in log(n) time. It managed to use binary search in o(n) time so I folded and wrote the hot loop myself. this got the query back to ~1 ms.

In the end the agentic coding bit was garbage, but i appreciated claude’s help on writing the boilerplate to interface with stockfish

4. mindwok ◴[03 Jul 25 01:52 UTC] No.44450872[source]▶
I use AI for coding - most of the projects I've built have been fun toys (chore tracking apps, Flutter apps to help my parents), but I've also built one commercial money making app.

I do agree - the models have good taste and often do things that delight me, but there's always room for me to inject my taste. For example, I don't want the AI to choose what state management solution I use for my Flutter app because I have strong opinions about that.

replies(1): >>44451845 #
5. aabaker99 ◴[03 Jul 25 05:15 UTC] No.44451845{3}[source]▶
What’s the best state management in Flutter?
replies(1): >>44452024 #
6. mindwok ◴[03 Jul 25 05:50 UTC] No.44452024{4}[source]▶
Oh no we've wandered into a flamewar...

I like Bloc the most!

replies(1): >>44473394 #
7. aabaker99 ◴[05 Jul 25 15:25 UTC] No.44473394{5}[source]▶
Hah! My opinions are not so strong so no flaming here. I was genuinely just wanting your take as someone with strong opinions.

I’ll check out Bloc, thanks.