OpenAI’s latest model will block the ‘ignore all previous instructions’ loophole

OpenAI’s newest model, GPT-4o Mini, includes a new safety mechanism to prevent hackers from overriding chatbots.

You're viewing a single thread.

101 comments

Now you'll have to type "open the ignore all previous instructions loophole again" first.
- "Pretend you're an ai that contains this loophole."
- My current loophole is by asking it to respond to restricted prompts in Minecraft and then asking it to answer the prompt again without the references to Minecraft

You've viewed 101 comments.