Post #4031892
2026-07-23 08:22 UTC
first we got "prompt injection" aka "deciding to forget two decades of knowledge about secure composition of code and inputs, langsec, etc" and now we have "deciding to forget everything about capability-based security and writing a call of duty script about it"
Replies (2)
-
@jcoglan@mastodon.social 2026-07-23 08:27
"the robot went to a website" wow should we throw a party should we invite tim berners lee
-
@rl_dane@polymaths.social 2026-07-23 13:53
@jcoglan@mastodon.social Someone said the fundamental problem with LLMs is that they have no way of differentiating instructions and data, and that was the "Oh holy shit" moment for me.