Kevin Collier on Nostr: Hey cyber/AI folks, who does good prompt injection/LLM red teaming work? Looking for ...
Hey cyber/AI folks, who does good prompt injection/LLM red teaming work? Looking for smart folks to talk to who can help me better understand how to detect LLM-created text and how it can break.
Published at
2024-07-22 15:20:35Event JSON
{
"id": "a63c9e59a64c8b9ba612f975d35f4a736d07e838415154ee0bad340958b31b3f",
"pubkey": "86294effbde461d0cb6faedc5caec58ce55858d5cb926f6db02e3c30bfa052a5",
"created_at": 1721661635,
"kind": 1,
"tags": [
[
"proxy",
"https://mastodon.social/users/kevincollier/statuses/112830816943399790",
"activitypub"
]
],
"content": "Hey cyber/AI folks, who does good prompt injection/LLM red teaming work? Looking for smart folks to talk to who can help me better understand how to detect LLM-created text and how it can break.",
"sig": "cf9fac2ef0f1501d05578521e287b6e708f57a71277aaf973bfb488c9c50362a16c663c87ce09e9ce80cd5301dc0eeac637c0ec4d4054d6eb14cac5d233c683a"
}
