Skip to main content
Tidy up post
Source Link
TylerDurden
  • 389
  • 1
  • 3
  • 7

Do developers not genuinely want to prevent them? It seems like if they are able to develop such impressive AI models then it wouldn’t be that difficult to create catch-all/wildcard mitigations to the various jailbreak methods that are devised over time.

What gives? (I.e.,i.e., what is so difficult about plugging these holes, or why might the developers not really want to do so?)

Do developers not genuinely want to prevent them? It seems like if they are able to develop such impressive AI models then it wouldn’t be that difficult to create catch-all/wildcard mitigations to the various jailbreak methods that are devised over time.

What gives? (I.e., what is so difficult about plugging these holes, or why might the developers not really want to do so?)

Do developers not genuinely want to prevent them? It seems like if they are able to develop such impressive AI models then it wouldn’t be that difficult to create catch-all/wildcard mitigations to the various jailbreak methods that are devised over time.

What gives? (i.e., what is so difficult about plugging these holes, or why might the developers not really want to do so?)

Why do chatGPTChatGPT “jailbreaks” work?

Do developers not genuinely want to prevent them? It seems like if they are able to develop such impressive AI models then it wouldn’t be that difficult to create catch-all/wildcard mitigations to the various jailbreak methods that are devised over time.

What gives? (IeI.e., what is so difficult about plugging these holes, or why might the developers not really want to do so?)

Why do chatGPT “jailbreaks” work?

Do developers not genuinely want to prevent them? It seems like if they are able to develop such impressive AI models then it wouldn’t be that difficult to create catch-all/wildcard mitigations to the various jailbreak methods that are devised over time.

What gives? (Ie, what is so difficult about plugging these holes, or why might the developers not really want to do so?)

Why do ChatGPT “jailbreaks” work?

Do developers not genuinely want to prevent them? It seems like if they are able to develop such impressive AI models then it wouldn’t be that difficult to create catch-all/wildcard mitigations to the various jailbreak methods that are devised over time.

What gives? (I.e., what is so difficult about plugging these holes, or why might the developers not really want to do so?)

Became Hot Network Question
Source Link
TylerDurden
  • 389
  • 1
  • 3
  • 7

Why do chatGPT “jailbreaks” work?

Do developers not genuinely want to prevent them? It seems like if they are able to develop such impressive AI models then it wouldn’t be that difficult to create catch-all/wildcard mitigations to the various jailbreak methods that are devised over time.

What gives? (Ie, what is so difficult about plugging these holes, or why might the developers not really want to do so?)