111–120 of 234 posts
Earlier quoted context omitted.
Lucky you. I always go "huh, so I wrote this?". And this was in the pre-AI era.
These feelings aren't mutually exclusive. I'm often like "I have no memory of this place" while my name stares at me from git blame, but that doesn't mean my intuition of how it's structured isn't highly likely to be right in such cases.
Code has become cheaper to produce than to perceive. Which means fixes can go in faster than it would require to first grok it What’s missing in literally every single one of these conversations is testing Literally all you have to do is implement test driven development and you solve like 99.9% of these issues Even if you don’t go fully TDD which I’m not a fan of necessarily having an extensive testing suite the cov…
There's another gap, actually. Imprecise specification. When you need to implement something yourself, you have to make decisions when faced with the reality of turning ideas into code. An AI agent sometimes surfaces these; and sometimes it just makes a choice. The risk is tests just embed these decisions as policy in code, without there have been proper consideration. Often there's a core ambiguity in a conception s…
So a poor specification is perfectly technically implemented won’t actually do what the intended goal is because the user has not correctly specified the goal and so ultimately it will fail at the highest level task if poorly specified
But that won’t necessarily reveal itself in code it would reveal itself in failure for other people to adopt or the user let’s say to adopt that tool for their workflow
And now programmers experience what is like to be a user, trying to comprehend the system on their computer screen. I propose a new paradigm: programmer experience, PX. So, code generated by AI ideally would follow the rules of PX. Whatever those may turn out to be.
Is this different from DX?
Also, the essay notes that once a "worse" system is established, it can be incrementally improved. Following that argument, we can say that as long as the AI code runs, it creates a footprint. Once the software has users and VC funding, developers can go back and incrementally improve or refactor the AI's mess, to a satisfying degree.
Earlier quoted context omitted.
If I’m learning for the first time, I think it matters to hand code something. The struggle internalizes critical thinking. How else am I supposed to have “taste”? :) I don’t know if this becomes prod code, but I often feel the need to create like a Jupyter notebook to create a solution step by step to ensure I understand. Of course I don’t need to understand most silly things in my codebase. But some things I need t…
Almost anything I write in Python I start in jupyter just so I can roll it around and see how it feels- which determines how I build it out and to some degree, how easy it is to fix issues later on. With llm-first coding, this experience is lost
The whole premise of the post, that coders remember what and why they wrote things from 6 months ago, is flawed. We've always had the problem that understanding while writing code is easier than understanding code you've written. This is why, in the pre-AI era, Joel Spolsky wrote: "It's harder to read code than to write it."
I recently did some work on a codebase I last touched 4 years ago. I didn't remember every line but I still had a very good grasp of how and why it's put together. (edit: and no, I don't have some extra good memory)
Richard Gabriel wrote a famous essay Worse Is Better ( https://www.dreamsongs.com/WorseIsBetter.html ). The MIT approach vs the New Jersey approach does not necessarily apply to the discussion of the merits of coding agent, but the essay's philosophy seems relevant. AI coding sometimes sacrifices correctness or cleanness for simplicity, but it will win and win big as long as the produced code works per its users' sta…
Why wouldn’t you ask AI to explain the architecture and code? It’s much better and efficient than any human.
One could argue with its stance, but I took it as a given (the equation for cognitive debt touches on science).
It feels entirely logical to view LLMs/coding agents as an almost final step in the short-term focus the overall system has been thriving on.
Management where I work is currently touting a youtube video from some influencer about the levels of AI development, one of the later ones being "you'll care that it works, not how". We are all supposed to be advancing through these levels. Moving at a pace where you actually understand the system you're responsible for is now considered a performance issue. But also, we're "still held responsible for quality". Need…