Because of jailbreaking, I don't think this generation's LLMs is appropriate for reply without a human approval for any anonymous endpoint.
If there isn't a human approving each reply, then the bot *can't* follow any policy. Anyone could ask the bot to violate all the policies of the Mastodon instance and the bot wants to please so it will comply.
🥥Matthew Martin🥥☑ /
npub1d3…sr8n4
2024-09-02 20:40:50
in reply to nevent1q…vta2
Author Public Key
npub1d3u7t3fcdmsuhedcqvpugrud0qvrrmmckc7wwmrjds7qk3lkyt0qesr8n4Published at
2024-09-02 20:40:50Event JSON
{
"id": "28fb53ee810895fb6957460369182c0f55b0a7b56591ef73a3682d6bf65a7024",
"pubkey": "6c79e5c5386ee1cbe5b80303c40f8d781831ef78b63ce76c726c3c0b47f622de",
"created_at": 1725309650,
"kind": 1,
"tags": [
[
"p",
"6c79e5c5386ee1cbe5b80303c40f8d781831ef78b63ce76c726c3c0b47f622de"
],
[
"e",
"0c785f70b88b25ba50b8968a9e474b0b6ca90f2180f8a2f1b376ee74be467a94",
"",
"reply",
"6c79e5c5386ee1cbe5b80303c40f8d781831ef78b63ce76c726c3c0b47f622de"
],
[
"proxy",
"https://mastodon.social/@mistersql/113069893273975134",
"web"
],
[
"e",
"21c5fbe4706e471deb287c8bef23b86c3b118615c2c7d747d77f95e067f476b2",
"",
"root",
"6c79e5c5386ee1cbe5b80303c40f8d781831ef78b63ce76c726c3c0b47f622de"
],
[
"proxy",
"https://mastodon.social/users/mistersql/statuses/113069893273975134",
"activitypub"
],
[
"L",
"pink.momostr"
],
[
"l",
"pink.momostr.activitypub:https://mastodon.social/users/mistersql/statuses/113069893273975134",
"pink.momostr"
],
[
"-"
]
],
"content": "Because of jailbreaking, I don't think this generation's LLMs is appropriate for reply without a human approval for any anonymous endpoint.\n\nIf there isn't a human approving each reply, then the bot *can't* follow any policy. Anyone could ask the bot to violate all the policies of the Mastodon instance and the bot wants to please so it will comply.",
"sig": "cfb12d0d3212d6e505162a0d6080bb616f99cdb12e2bf338325e0d70f1536c66bcc383922876cc2f0ecc76d6286f80aecdaf87bd8b0f82b0b226f9db987cf4e4"
}