DrMikeWatts on Nostr: Giving instructions in hexadecimal can defeat AI guardrails, in this case tricking ...
Published at
2024-11-08 02:38:29Event JSON
{
"id": "d5c56f7d444466478149cb54b55df9d6e285d0e7bf5a1bd8c8efe276f0e6eb75",
"pubkey": "ea28837ca4d967d53bcd551565de4eb3cbcfd558a10c1ab2825999f8e8cc991c",
"created_at": 1731033509,
"kind": 1,
"tags": [
[
"t",
"ai"
],
[
"t",
"artificialintelligence"
],
[
"proxy",
"https://newsmast.social/users/DrMikeWatts/statuses/113445012047024897",
"activitypub"
]
],
"content": "Giving instructions in hexadecimal can defeat AI guardrails, in this case tricking ChatGPT into writing exploit code: https://www.theregister.com/2024/10/29/chatgpt_hex_encoded_jailbreak/ \n#ai #artificialintelligence",
"sig": "12d8d90a970de7e5d1f4eceea986a2fafbe8b0ca2dc4ed42cbdefb39d67511fb840dd11de2be823f3b1bdaf7a15c7df7aa1233ca25e579b5e0c988d241c4ef0b"
}
