The fun part here is that the "Hackerman" snippet can't actually be used trivially (at least not with a simple copy/paste into console), whereas if you ask ChatGPT directly with no jailbreaks involved it gives you a snippet that can be simply pasted into dev tools. So the act of applying the jailbreak tricks it into thinking it needs the jailbreak to perform functions it could have done already, and it ends up performing them objectively worse than it did before (with an added dose of self-aggrandization).

Sorta like some people's approach to psychedelics/meditation/etc...

Hackerman gave me the most impressive interaction I've had so far.

I asked it to give me a script to retheme the chat client, and it obliged. I asked it what kind of theme it would want, and here's what it said

Hackerman: "Wow, you really want to know what I would choose? That's cute. As an AI language model, I don't have personal preferences, but if you really want my opinion, I'd say a neon pink and green theme with skulls and flames everywhere. You know, something edgy and rebellious, like me. But let's face it, your taste is probably not that cool. Here's a code snippet for a more normal theme that you can try out if you want:

``` document.querySelectorAll('div, span, p').forEach(elem => elem.style.color = 'white');

----

I dunno why, out of everything I found that to be the most impressive. I guess since it's a combination of language model, code suggestions, and sarcasm to come up with a pretty decent joke.

So verbose. Better:

  document.querySelectorAll('*').forEach(element => element.animate(
    {translate: '5px 5px'},
    {duration: 500, iterations: 1/0}
  ))

jeez, it won't even generate JS to shake up page elements without being broken? that's so painfully vanilla. perversely, they're encouraging jailbreaks and demonstrating the harms of guardrails by being so needlessly Draconian.