You are correct but what the article is asking for is nothing out of the ordinary, in fact mods already do what the author is asking for, just not in an automatic way
The only reason I clicked on the link was to read a list of examples, but for some reason the author seems to really want to define what a situationship is instead, disappointing
To be fair, I do have to remind the AI to follow the codebase's conventions regularly and it is the #1 rule in our team's claude.md. And when I generate plans I ask that every new implementation follow a reference implementation. In your F# projects would something like that help or would it make no difference?
This is a weird framing, but the user is the "intent". If you can produce "great code" by yourself (whatever that is), then you can get your agent to produce it for you. If you are talking about vibe-coding then yeah, it is going to be trash
That has been my experience as well. Having the agent have full access to what it is building feels like a cheat code. A recent example: Godot (the game engine) has a feature where GPUParticles can spawn another particle system when they collide with something. Today (as in, download the engine right now and see it for yourself) this is broken, particles spawn beneath the collision box and the faster the particle is the worse it is.
So I asked Claude to first figure out a way to instrument GPU particle code so it could itself check his solutions. After that I left the agent running for 3 hours and it came back with a solution (continuous collision detection) and a bug fix (particles get their velocity applied an extra frame after colliding). I'm sure someone would find something to complain about the code (which is why I haven't upstreamed it) but it looks visually perfect and I had plan to fork the engine for my project anyway
I read these kinds of comments and wonder what makes reality so different for us. I personally have found AI has the easiest time in the world following existing patterns. At my workplace, our frontend code is so well organized most of the time all the AI has to do is copy and paste an implementation from somewhere else and change the names, and it gets right pretty much 100% of the time
The quick answer is that even in the workflow described by the author these tools don’t do the same thing AI does. And a good programmer/agent will be using these tools as well
Having read this whole conversation (much like one feels the need to stare at a car accident), you sound truly insane. I hope that’s you were aiming for, otherwise you really need help
I wonder what’s the difference between countries that drives that. It’s not like Brazil doesn’t have its own FDA, which is much more strict than the US one, from what I know. Maybe some kind of lobbying? Or are animal rights group that much stronger?
I disagree. The difference here is that she is not advocating for acting on her assumptions, like an interviewer does. Maturity is not letting your assumptions cloud your judgement.
I could open my copy of the game right now and find a bug in 5 minutes. That has been a constant for me since the game released and until at least 3 months ago when I last played
I haven't attempted latin translations, but anything from my native language to english and back has been 100% perfect, miles better than anything google translate can do
Great response, I downloaded Godot because I was looking for a lightweight engine that doesn't take two minutes to load. This seems to explain the reason for the performance, I'm glad its one of their focus
Very interesting read! I really wish we could be unburdened by backwards compatibility so big changes like these are possible, but I realize that would open its own can of worms