arbitraryidentifier

joined 2 years ago

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.

[–] arbitraryidentifier@awful.systems 7 points 1 month ago (2 children)

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

murder as virtue signaling

They're going to have their AI watch it and summarize it for them so then can nod their head and go "mmhm" and know that they are truly the pioneers of the Future...

Both customers will still be able to get Horizon Worlds on a mobile phone

I loled

AI as the realization of Huey Lewis and the News iconic hit song "I Want a New Drug"

[–] arbitraryidentifier@awful.systems 2 points 4 months ago* (last edited 4 months ago)

ads that don't suck

does not compute

Ran across https://406.fail/ and had a chuckle.

the proof of the art is in the tasting

yeah i wasn't sure until i saw that

[–] arbitraryidentifier@awful.systems 1 points 10 months ago (1 children)

Was it the "Hyperreal Simulacrum" from the joe rogan takedown videos you linked in last weeks stubsack?

view more: next ›