71–80 of 80 posts
Earlier quoted context omitted.
The time might come when the ai just writes things like http request parsers and crypto libraries on the fly. And it will be somewhat normal
I was assured manufacturing was dead because we'd all be 3D printing everything we need in our garages.
Earlier quoted context omitted.
It’ll just spit the code out. I vibe coded some with cookie handling the other day that worked. Should I have done it? Nope. But the ai did it and I allowed it The concept of using a library for everything will become outdated
The value of a library is not just that it does a thing you want, but that it doesn’t do all the things you’d prefer it didn’t. It’s easy to write a cookie parser for a simple case; clearly your robot was able to hand you one for millidollars. How confident are you that you’ve exhaustively specified the exact subset of situations your code is going to encounter, so the missing functionality doesn’t matter? How confid…
This article is lumps design and implementation together. In my experience, LLMs are really quite bad at designing anything interesting. They are sort of tolerable at implementation — they’re remarkably persistent (compared to humans, anyway), they will tirelessly use whatever framework, good or bad, you throw at them, and they will produce code that is quite painful to look at. And they’ll say that they’re architect…
And I wouldn't write this article 3 months ago. Since then the quality of the output jumped significantly, it is now possible to put the agent into a proper harness (plan/edit/review/test) and the output is good — and if it's not, you discard it and try again, or point out a detail for the next cycle of improvements.
Yes, this requires a lot of forethought to set up, but it works.
I'm not talking only about "web things", I'm working on a project that involves engineering calculations and a lot of optimization of hot paths, both CPU and GPU.
This article is lumps design and implementation together. In my experience, LLMs are really quite bad at designing anything interesting. They are sort of tolerable at implementation — they’re remarkably persistent (compared to humans, anyway), they will tirelessly use whatever framework, good or bad, you throw at them, and they will produce code that is quite painful to look at. And they’ll say that they’re architect…
>LLMs are really quite bad at designing anything interesting Let’s be honest, how many devs are actually creating something interesting/unique at their work? Most of the time, our job is just picking the right combination of well-known patterns to make the best possible trade-offs while fulfilling the requirements.
Earlier quoted context omitted.
Why does the AI need hardware/chips? Why does the AI need the universe to exist? Why does the AI need math/logic to exist? Using these preexisting will all become outdated. You will look like primitive cavemen if your agents don't build these from scratch every time you build $NEXT_BIG_THING. Even local LLMs will be able to build these from scratch by end of 2026.
Yeah I actually think the very concept of software will see agents affect out. Agents will do what you used to code. And it will be automatic
Earlier quoted context omitted.
Today I asked an LLM (Codex whatever-the-default-is) to implement something straightforward, and it cheerfully implemented it twice , right next to each other, in the same file, and then wrote the actual code that used it and open-coded a stupendously crappy implementation of the same thing right there. The amazing thing is that the whole mess kind of worked.
Right. Kind of works is their MO at the moment. I do try to keep in mind that just because something sucks at the moment, that doesn't mean that it will always suck (especially when you pour _trillions_ of dollars into it)
This article is lumps design and implementation together. In my experience, LLMs are really quite bad at designing anything interesting. They are sort of tolerable at implementation — they’re remarkably persistent (compared to humans, anyway), they will tirelessly use whatever framework, good or bad, you throw at them, and they will produce code that is quite painful to look at. And they’ll say that they’re architect…
I was wondering if our goal is to leverage them to think about interfaces a bit, like a slightly accelerated modeling phase and then let them loose on the implementation (and maybe later let them loose on local optimization tricks)
> …a slightly accelerated
> modeling phase and then
> let them loose on
> the implementation…
_____
MODEL
…
The Verdict: If you provide a clear instruction like "Before you touch the code, read architecture.puml and ensure your changes do not violate the defined inheritance/dependency structure," the agent will be very effective at following it.
If you just "hope" it bears it in mind, it probably won't.
_The agent is a tool, not a mind-reader; it will take the shortest path to a passing test unless you wall that path off with your architectural models_.
…
To make it actually work, you need to turn the UML from a "suggestion" into a "blocker." You should add a section to your AGENTS.md (or CLAUDE.md ) that looks like this:
1. Tool Trigger: By using words like "…"
Why this works:
…
_____
Earlier quoted context omitted.
Yeah I actually think the very concept of software will see agents affect out. Agents will do what you used to code. And it will be automatic
Yeah, who needs things like PyTorch? Let agents do that!
Earlier quoted context omitted.
This take is just an intermediary take until ai takes over software engineering. In the same way, eventually self driving cars will make human drivers look dangerous I think your thought process is not taking into account what a super logical ai can do, and how effortlessly it could generate some of this code.
> effortlessly Real question: does your world model suppose super exponential gains in intelligence and efficiency?
Earlier quoted context omitted.
I was wondering if our goal is to leverage them to think about interfaces a bit, like a slightly accelerated modeling phase and then let them loose on the implementation (and maybe later let them loose on local optimization tricks)
> …a slightly accelerated > modeling phase and then > let them loose on > the implementation… If you mean _visual_ modeling ala UML [1], then I have it on " good authority " [2] that's a sound approach… _____ MODEL … The Verdict: If you provide a clear instruction like "Before you touch the code, read architecture.puml and ensure your changes do not violate the defined inheritance/dependency structure," the agent wil…