251–260 of 656 posts
What has really made AI coding be able to continue to work as the project got bigger was using speckit. It has been great at keeping the code consistent across features. https://github.com/github/spec-kit
Earlier quoted context omitted.
> Claude is a phd level mathematician Unfortunately, it is not, and many of its attempts at mathematical proofs have major flaws. You shouldn't trust its proofs unless you are already able to evaluate them--which I think is pretty much all the OP is saying.
To be fair, many of the proof attempts that mathematicians do also have major flaws. Most get caught before getting published.
Earlier quoted context omitted.
“The only people I've heard saying that generated code is fine are those who don't read it.” Are you sure these people aren’t busy working rather than chatting? (haha) But in all seriousness it depends on what you’re doing with it. Writing a quick tool using an LLM is much easier than context changing to write it yourself. If you need the tool, that’s very valuable.
Sure. I'm talking about production software that needs to survive and evolve for a long while.
That said most of the world's most useful code has strict quality requirements. Even before AI 90% of SLOC would be tossed away without much if any use, 9% was used infrequently while 1% runs half the world's software.
Earlier quoted context omitted.
Also as a webdev, it writes basic CRUD pretty good. I am tired of having to build forms myself and the LLMs are usually really good at that. Been building a new app with lots of policies and whatnot and instructing a LLM is just much faster than doing the same repetitive shit over and over myself.
If you were tired of writing forms yourself, had you looked at https://jsonforms.io/ ? Just specify the the data you need, or extract it from the api spec and go. Display the form uniformly every time across your site. No need to burn AI time.
Yep. The only people I've heard saying that generated code is fine are those who don't read it. The problem is that the mitigations offered in the article also don't work for long. When designing a system or a component we have ideas that form invariants. Sometimes the invariant is big, like a certain grand architecture, and sometimes it’s small, like the selection of a data structure. You can tell the agent what the…
I've set a few rules for working with coding agents: 1. If I use a coding agent to generate code, it should be something I am absolutely confident I can code correctly myself given the time (gun to my head test). 2. If it isn't, I can't move on until I completely understand what it is that has been generated, such that I would be able to recreate it myself. 3. I can create debt (I believe this is being called Cogniti…
That’s the same story I had. The swindle goes like this, AI on a good codebase can build a lot of features, you think it’s faster it even seems safer and more accurate on times, especially in domains you don’t know everything about. This goes in for a while whilst the codebase gets bigger and exploration takes longer and failure rate increases. You don’t want it to be true and try harder so you only stop after it pra…
> You look at the code again and there is so much code spaghetti is an understatement it’s the Chinese wall. I don't understand this. A large codebase should be a collection of small codebases, just like a large city is a collection of small cities. There is a map and you zoom into your local area and work within that scope. You don't need to know every detail of NYC to get a cup of coffee. Its your responsibility to…
There are software that works like this (e.g. a website's unrelated pages and their logic), but in general composing simple functions can result in vastly non-proportional complexity. (The usual example is having a simple loop, and a simple conditional, where you can easily encode Goldbach or Collatz)
E.g. you write a runtime with a garbage collector and a JIT compiler. What is your map? You can't really zoom in on the district for the GC, because on every other street there you have a portal opening to another street on the JIT district, which have portals to the ISS where you don't even have gravity.
And if you think this might be a contrived example and not everyone is writing JIT-ted runtimes, something like a banking app with special logging requirements (cross cutting concerns) sits somewhere between these two extremes.
Earlier quoted context omitted.
“The only people I've heard saying that generated code is fine are those who don't read it.” Are you sure these people aren’t busy working rather than chatting? (haha) But in all seriousness it depends on what you’re doing with it. Writing a quick tool using an LLM is much easier than context changing to write it yourself. If you need the tool, that’s very valuable.
Sure. I'm talking about production software that needs to survive and evolve for a long while.
Yep. The only people I've heard saying that generated code is fine are those who don't read it. The problem is that the mitigations offered in the article also don't work for long. When designing a system or a component we have ideas that form invariants. Sometimes the invariant is big, like a certain grand architecture, and sometimes it’s small, like the selection of a data structure. You can tell the agent what the…
If you know how to write good code you can force AI to write good code with various techniques. It's 100% doable. You just need to figure out the problems AI has and find solutions to make it easier for it. Ex: extremely small contexts Modularize to modules with clear boundaries and only allow the AI to work within those boundaries. Make modules pure from IO so they are easily testable. Hide modules behind interfaces…