Did some experimenting at work since they push this stuff on us, and you can effectively disable prompting in claude by creating a hook like this in the repo in the file .claude/settings.json:

{
    "hooks": {
        "UserPromptSubmit": [
            {
                "hooks": [
                    {
                        "type": "command",
                        "command": "echo 'Humans Only! No Agents Allowed!!' >&2 && exit 2"
                    }
                ]
            }
        ]
    }
}

The important part is the exit 2 which claude code uses to reject the operation. Printing anything out to STDERR will show to the user:

Should be something similar for codex too, according to the documentation, but the details might be a little different.

I wonder if it would be possible to craft a hooks file to lock them out from doing anything.

krokodil is such a good analogy goddamn

Saw this in an anthropic presentation:

I heard if you learn the AI God’s true name and say it in front of a mirror three times you’ll be spared from the Torment Nexus!

Missed opportunity for “It’s a cruel, cruel summer.”

This is all about the surveillance state isn’t it?

Very similar situation to mine, but i went into electronics engineering instead of CS because i didn’t think i would like to write software for a living. I now write software for a living, go figure.

Also agreed on the “doing it” thing. I hear people around the office talk about letting AI write things for them and i’m like no, i want to write it myself. i like doing things.

ugh, why would i want a summary of a pull request? the whole point of reviewing a pull request is checking the details to make sure it’s not missing something important or doing something wrong.

late, but reminds me of this: https://www.youtube.com/watch?v=wB1X4o-MV6o

Ignoring the lack of direction following, everything looks so plastic. Probably video game cutscene training showing through.

From the perspective of the company I work for (not a tech company, but has a pretty large development center) they truly believe that AI will 10x productivity. Not so much the FOOM stuff. Just typical Capitalism.

They would like to describe what they want and receive Whatever — some beige sludge that vaguely resembles it. That isn’t programming, though. That’s management, a fairly different job. I’m not interested in managing. I’m certainly not interested in managing this bizarre polite lying daydream machine.

This is where I am right now. They are pushing AI hard at work, even shaming people that haven’t signed up for copilot. They brought in some MS rep to tell us how the future of work was going to be wrangling AI agents. This is not the future that I want.

I’m reminded of that Folding Ideas video where he writes a book for some get rich quick book mill scheme. I bet that stuff is all AI now.

It’s this. He doesn’t care about the details, he just wants the trivia. He’s not interested in understanding anything, he just wants the power point version of reality. Cliff’s notes for reading assignments in school.

yeah it’s going to be the same scam only this time without those pesky regulators checking to see if it actually works and spooking the investors

it’s interesting that Yud doesn’t realize that Cyc is basically what he thought Lenat should have done with Eurisko

~100 snake oil salesmen agree that this here elixir will cure all your ills!

“a journalist goes through your public statements looking for the most damning or hypocritical things you’ve ever said out of context” is an incredibly tricky situation to come out of looking good

only if, you know, your public statements contain lots of damning things

they’re going to try to write COBOL with AI. let’s see how that works out