TechEcho

I don't know why anyone cares. You're still violating the OpenAI usage policy. You'll get to have fun for maybe a day before they ban you.<p>It's especially pointless as running local LLMs gets better and easier all the time, and there are plenty that will discuss whatever edgy topic gets you excited.

"Oops. I accidentally gave a step-by-step guide to make MDNA."<p>This just makes me think that we are near some local maximum. By now these models have been endlessly refined, but they're still just as vapidly stupid and dangerous to run unsupervised as they were 5 years ago. Human-like performance is not to be found on this particular hill.

This has been a well known “attack” since function calling was introduced. They’re essentially doing exactly that with their prompt.

Are there dark web marketplaces for LLM jailbreaks yet, like there are for 0-days, or we not quite there yet?

What does “jailbreak” mean in this context?<p>Not sure what “bad” things are happening here?

Didn't work when I tried it, while other jailbreaks still work.

This has been a well known “attack” since function calling was introduced. They’re essentially doing exactly that with their prompt.

Are there dark web marketplaces for LLM jailbreaks yet, like there are for 0-days, or we not quite there yet?

What does “jailbreak” mean in this context?<p>Not sure what “bad” things are happening here?

Didn't work when I tried it, while other jailbreaks still work.

GPT-4o Jailbroken by Claiming It's an "All-Responsive" API Endpoint

6 comments

GPT-4o Jailbroken by Claiming It's an "All-Responsive" API Endpoint

6 comments