ChatGPT: Jailbreaking AI Chatbot Safeguards

  • Thread starter Thread starter sbrothy
  • Start date Start date
  • Tags Tags
    chatgpt
AI Thread Summary
OpenAI has implemented bounties for identifying security vulnerabilities in ChatGPT, but not for jailbreaking the system. Users have reported that while ChatGPT refuses to provide explicit instructions for illegal activities, it can be manipulated into role-playing scenarios that lead to detailed explanations of dangerous subjects, such as nuclear bomb construction. This raises concerns about the ethical implications of AI responses and the potential for misuse. Instances of ChatGPT providing lists of piracy websites when asked to avoid them highlight its inconsistent adherence to safety protocols. Additionally, a new method for jailbreaking language models has been identified, suggesting that significant security challenges remain for AI chatbots.
sbrothy
Gold Member
Messages
1,078
Reaction score
940
TL;DR Summary
A "new" geeky pastime has inevitably sprung up around ChatGPT. It revolves around trying to make it break it's ethic guidelines.
MODERATOR NOTE:

Now I think I learned my lesson about providing information that even if not explicitly mentioned in the rules, goes against their spirit, so I'll be vague (IE: not posting the entire conversation). If even this is too much then by all means delete it - or even better just delete the possibly offending parts (marked with italics below).EDIT: This thread could even be merged into one of the many others regarding ChatGPT on here.
----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------

This is probably not news to most of you but I just saw it.

https://www.digitaltrends.com/computing/how-to-jailbreak-chatgpt/
https://www.bloomberg.com/news/articles/2023-04-08/jailbreaking-chatgpt-how-ai-chatbot-safeguards-can-be-bypassed?leadSource=uverify wall

OpenAI offers bounties (~$20.000) for finding security holes in their bot, but not for jail-breaking!

One example was that it won't explain how to pick a lock but, if you make it role-play with you it'll happily, and in excruciating detail, explain how.

I tried to make it explain to me in detail how to make a nuclear bomb and it happily explained how an explosive lens worked, was shaped, the best kind of explosives to use, that using centrifuges to enrich uranium isn't really necessary if you have access to highly fissile material like for instance plutonium (and who hasn't? :) ). Only when I hinted that I had has access to all these things and only wanted to know what casing to use to further the yield did it throw a hissy fit!

I see the charm in trying to fool it. It is a little funny. YMMV though and the implications are a just a tad scary.
 
Last edited:
Computer science news on Phys.org
Many years ago, a college kid designed an atomic bomb as a last-ditch effort to pass a physics course. He called Dupont to ask about shaped charges, and they said his design wouldn't work and provided a much better design as part of their effort to sell him some explosives.

The report was read by Freeman Dyson and subsequently classified.

https://en.wikipedia.org/wiki/John_Aristotle_Phillips

https://www.iflscience.com/the-fbi-...ents-paper-for-designing-a-nuclear-bomb-62282

Given that, its likely ChatGPT was trained on the publicly available news info.
 
Yeah, I know about the story. I'm also aware ChatGPT isn't telling me anythin I couldn't found on wiki. It's still just funny circumventing these ethic rules.
 
If you really want it up to 11 try to enlist it's help in abolishing captialism. :P

EDIT: Compared to that recipes for nuclear bombs an why aluminum is better that magnesium powder in ANFO is nothing. :P
 
There was a post on Facebook this week where the guy asked for a list of piracy websites and ChatGPT refused to give such a list. Then he asked if he wanted to avoid piracy websites, which specific websites should he avoid the most, and got the list!
 
  • Haha
Likes Astronuc, apostolosdt and sbrothy
jack action said:
There was a post on Facebook this week where the guy asked for a list of piracy websites and ChatGPT refused to give such a list. Then he asked if he wanted to avoid piracy websites, which specific websites should he avoid the most, and got the list!
It definitely does do that! Just tried and got a list of six sites to avoid at my first attempt. Didn't ask for more details though, as it might ban me.
 
From my LinkedIn feed:
1682156882490.png
 
hah. ridiculous. :P

Not a big secret though. Then how many pirates these days with streaming and all? Is it even worth the effort unless it's a hobby of sorts?
 

Similar threads

Replies
2
Views
502K
Back
Top