Hacker News Reader

Comment by mccoyb | Hacker News Reader

Loops work when you spend the proper amount of time to understand what you want ahead of time. The prerequisite is clarity — enough clarity that you could write a careful specification that you could hand off to a junior colleague.

Often, it takes 5-6 broken crappy versions of a thing until you understand that. There is no accelerating the 5-6 broken crappy versions - there’s no agent tech that’s going to help your meat brain avoid thinking time.

So most of my time is iterating between these two phases: I don’t understand what I want, I need to read and write and play with code, okay it’s been long enough I think I know what I want (it is extremely easy to deceive yourself) … okay now I do actually know what I want and I can write a loop.

Many people think they can jump ahead with agents. You cannot fake understanding or clarity. It is painfully obviously when someone skipped that meat brain understanding phase.

View on HN

I had codex write a tool to extract all my pi sessions. (Had to filter out my prompts from the agents talking to subagents).

Then I had it analyze the patterns i was making and turned that into the flowchart for the outer guidance-creating-prompt.

I didn't have to spend too much time thinking what i wanted. I wanted it to do that.

The result is still mixed, and i'm not trusting it with delicate code bases, but for a game i've been building i dropped my check-in time to 1/5th i was previously spending on it.

Thats not a good thing per-se. I'm sure i'm missing good ideas by _not_ spending time with it. But previously I really had stagnated with my prompts becoming mechanical #now-do-this and #now-review-that with 90% of its suggestions being correct.

Just need to (automatically) remind it to "do the hard stuff first, clean up & refactor as you go" as well as a "reflect on your work" after its first return to get it to spill the beans on any crap left behind, and then process that in the guidance-creating-prompt to dish out new work.

I'm having it build the software to run a raspberry pi and using a local llm and opencode. the display code is fugly, and i regret nothing about how it'll look inside nor do I want to know all the stupid requirements. We improved it'd render speed by finding a github example using numpy. It uses jinja to render user generated templates for the ui.

The only problem it runs into is the bizarre BGRA or RGB or whatever color mapping between screen and frame buffer; it absolutely has no idea what it does when it's right. It also thinks there's some magic around the bits per pixel.

I do not really care, as this thing won't ever be extended beyond display some text and a few graphics. So why do I need it taking up space in my brain.

A lot of little projects are a lot easier now, but corpos who think this will be a magic want to their largesse of badly maintained code are gonna have trouble.

> Often, it takes 5-6 broken crappy versions of a thing until you understand that. There is no accelerating the 5-6 broken crappy versions - there’s no agent tech that’s going to help your meat brain avoid thinking time.

Fully agreed. Though I found that, once I found a harness (prompt + skills + model) that I trust to do most things the way I like it, it has sped up the coding/exploration part of that process.

Although the iterations are faster, it's still taking me almost the same amount of effort to go through those crappy versions, because I still need to understand and adjust my mental model of what ideas, principles, design apply for the solution, and what to try next.

So, in the end, I do feel like I'm expending more mental effort in a shorter amount of time (with some effort saved on writing the code, which wasn't that much to begin with once you're proficient). It's a weird feeling, like I'm "only" prompting and reading code, but I feel equally mentally spent, or sometimes more because of the compressed iteration cycle.

Reply on news.ycombinator.com