Not the person you asked, but I do that sometimes. For instance, when I want to watch a specific video but I don’t want having watched it to affect other video recommendations.

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.

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.

Software developer, here. (No, not a “vibe coder.” I actually know how to read and write my own code and what it does.)

Just had the opportunity to test GPT 5 as a coding assistant in Copilot for VS Code, which in my opinion is the only legitimately useful purpose for LLMs. (No, not to write everything for me, just to do some of the more tedious tasks faster.) The IDE itself can help keep them in line, because it detects when they screw up. Which is all the time, due to their nature. Even recent and relatively “good” models like Sonnet need constant babysitting.

GPT 5 failed spectacularly. So badly, in fact, that I’m glad I only set it to analysis tasks and not to any write tasks. I will not be using it for anything else any time soon.