Bit concerning that some professional engineers don't understand this given the sensitive systems they interact with.

"my calculator can perfectly add any numbers up to its memory limit" This kind of anthropomorphic language is misleading in these conversations. Your calculator isn't an agent so it should not be expected to be capable of any cognition.

Isn't this obvious? There is not enough latent knowledge of math there to enable current LLMs to approximate anything resembling an integral.

Replace tool with one of piano|guitar|etc and see your logic fall apart. Software tools like any other have a manual and require effort and time to learn.

This is still possible. Vibe coders are just not interested in working on a piece of software for years till it's polished. It's a self selection pattern. Like the vast amount of terrible VB6 apps when it came out. Or the state of JS until very recently.

It is indeed hard but the guys at Codeberg are certainly an order of magnitude better than Github as they opted out of the main AI crawlers, regularly block IPs known to belong to AI startups and they allow you to make your repos only be accessible to logged in users.

You seem be going on a tangent, here. Main point was about performing a well documented test anyway.

Are you planning on carrying out the experiment? Regardless of the outcome, it would be of value to developers.

This is not something you really want to happen for the health of the web tech ecosystem. I am surprised to see actual developers nonchalantly suggesting this. A type system for the web is not worth an IE 2.0

This is likely the future.

That being said: "I used to spend most of my time writing code, fixing syntax, thinking through how to structure the code, looking up documentation on how to use a library.".

If you are spending a lot of time fixing syntax, have you looked into linters? If you are spending too much time thinking about how to structure the code, how about spending some days coming up with some general conventions or simply use existing ones.

If you are getting so much productivity from LLMs, it is worth checking if you were simply unproductive relative to your average dev in the first place. If that's the case, you might want to think, what is going to happen to your productivity gains when everyone else jumps on the LLM train. LLMs might be covering for your unproductivity at the code level, but you might still be dropping the ball in non-code areas. That's the higher level pattern I would be thinking about.

I will imagine that in the future this will be tackled with a heavy driven approach and tight regulation of what the agent can and cannot touch. So frequent small PRs over big ones. Limit folder access to only those that need changing. Let it build the project. If it doesn't build, no PR submissions allowed. If a single test fails, no PR submissions allowed. And the tests will likely be the first if not the main focus in LLM PRs.

I use the term "LLM" and not "AI" because I notice that people have started attributing LLM related issues (like ripping off copyrighted material, excessive usage of natural resources, etc) to AI in general which is damaging for the future of AI.

Is your AI PR publicly available in github?

Why don't you prove it?

1. Find an old large codebase in codeberg (avoiding the octopus for obvious reasons)

2. Video stream the session and make the LLM convo public

3. Ask your LLM to remove jQuery from the db and submit regular commits to a public remote branch

Then we will be able to judge if the evidence stands