There’s also the fact that what we are currently calling AI isn’t, that there are better options that aren’t environmental catastrophes (I’m hopeful about small language models), and that no one seems to want all the “AI” being jammed into every goddamn thing.

No, I don’t want Gemini in my email or messaging, I want to read messages from people myself. No, I don’t want Copilot summaries of my meetings in Teams, half the folks I work with have accents it can’t parse. Get the hell out of my way when I’m trying to interact with actual human beings.

And I say that as someone whose job literally involves working with LLMs every day. Ugh.

You’re studying to be a programmer, right? You don’t mention your comfort language, so I’m going to try to keep this language agnostic.

Here’s what you do:

1. Figure out the absolute simplest application you could possibly build. I’m going to suggest a to-do app, because it’s traditional and it’s a dead simple concept.
2. Figure out the absolute simplest version of that application. I’m thinking it just renders a hard-coded list of to-dos with exactly one piece of interactivity, a button to cross off an entry.
3. Add another piece of interactivity: Make the rendered text of a to-do entry editable.
4. Add another piece of interactivity: Make the list resettable, so your edits and cross-offs vanish.
5. Add another piece of interactivity: Make it possible to add entries to the list.
6. Add another piece of interactivity: Make it possible to turn the list green.
7. Add another piece of interactivity: Make it possible to remove entries from the list.
8. Keep adding visible features until the frontend is the best goddamn to-do list you can make.
9. Create a backend. Your backend has a database (such as MySQL). It has one table, which contains every to-do.
10. Your backend should expose a REST API. If you don’t know what that is, read up on it. They’re very simple. Long story short, it’s a means of sending and receiving structured JSON.
11. Here’s where your app gets real: The REST API can read from and write to the database. That means no more hard-coded entries on the frontend. Your frontend will now read from the REST API when it loads, and populate the to-do list from it. When you delete an entry, it will be removed from the database. When you cross one off or turn it green, it will change in the database.
12. Congratulations, you’ve built a rudimentary real-world application!

Which is why I have never and will never download the app, go to the website, or otherwise watch any TikTok content.

I still have enough of an attention span to read actual books and watch full-length movies, and I want to keep it that way.

Dunno why you’re being downvoted, that there was a solid reference.

I set up a WAF for my company’s publicly facing developer portal to block out bot traffic from assholes like these guys. It reduced bot traffic to the site by something like - I kid you not - 99.999%.

Fucking data vultures.

Coordinated SLM governors that can redirect queries to the appropriate SLM seems like a good solution.

How the hell are they going to sustain the expense to power that? Setting aside the environmental catastrophe that this kind of “AI” entails, they’re just not very profitable.

Yep, that’s also pretty safe.

Are you using Copilot in agent mode? That’s where it breaks shit. If you’re using it in ask mode with the file you want to edit added to the chat context, then you’re probably going to be fine.

I’ve tried threats in prompt files, with results that are… OK. Honestly, I can’t tell if they made a difference or not.

The only thing I’ve found that consistently works is writing good old fashioned scripts to look for common errors by LLMs and then have them run those scripts after every action so they can somewhat clean up after themselves.

I have to test it with Copilot for work. So far, in my experience its “enhanced capabilities” mostly involve doing things I didn’t ask it to do extremely quickly. For example, it massively fucked up the CSS in an experimental project when I instructed it to extract a React element into its own file.

That’s literally all I wanted it to do, yet it took it upon itself to make all sorts of changes to styling for the entire application. I ended up reverting all of its changes and extracting the element myself.

Suffice to say, I will not be recommending GPT 5 going forward.

At my company, we had to implement all sorts of WAF rules precisely for that reason. Those things are fucking aggressive.

Beginning of Stray: “Oh, this cat game is so cute!”

End of Stray: [Hey, come see this big, grown-ass adult guy start ugly-crying!]