Taggart :ifin: on Nostr: This is a masterful demonstration of the unsecurable nature of LLMs, and how prompt ...
This is a masterful demonstration of the unsecurable nature of LLMs, and how prompt injection by dedicated humans who know how to write will always win.
https://role-confusion.github.io/Published at
2026-06-28 22:09:18 UTCEvent JSON
{
"id": "d6a1da335f42de50d3de2d62bfa2aada2f964951f068b6b548a6af88b672fa14",
"pubkey": "3ba412ac4b14c4b37cd6ed16b9d262ad4ffefb05c5b6c6b3e15e381471b1221a",
"created_at": 1782684558,
"kind": 1,
"tags": [
[
"proxy",
"https://infosec.exchange/users/mttaggart/statuses/116830015225440372",
"activitypub"
],
[
"client",
"Mostr",
"31990:6be38f8c63df7dbf84db7ec4a6e6fbbd8d19dca3b980efad18585c46f04b26f9:mostr",
"wss://relay.ditto.pub"
]
],
"content": "This is a masterful demonstration of the unsecurable nature of LLMs, and how prompt injection by dedicated humans who know how to write will always win.\n\nhttps://role-confusion.github.io/",
"sig": "efba0932498244e47cb59633455ae821c82640907226e4d3a26e67ef99001725619aaa874e3a9dc5ec613fa1665cfebf3b696f7c5eb07cd0a259f2d7e22306ff"
}
