Post B17VSWs05Dl61qfCvg by mttaggart@infosec.exchange
 (DIR) More posts by mttaggart@infosec.exchange
 (DIR) Post #B17VSWs05Dl61qfCvg by mttaggart@infosec.exchange
       2025-12-10T17:07:37Z
       
       0 likes, 1 repeats
       
       You may be tempted to think of prompt injection attacks against language models as "social engineering." Resist this temptation. Prompt injection is a mathematical attack against a non-deterministic system. Language may be the substrate, but the substance is numerical vectors. In other words, thinking of the attack as human language is a pointless limitation. The possibilities of what can go into the prompt to produce undesirable output are functionally infinite. Poetry, context shifting, and other human-like attacks are only the beginning. What comes next is a weaponization of the linguistic form in ways that seem utterly alien to human readers. But to the models, it's all just elements in the matrix.
       
 (DIR) Post #B17aka9H8DefBGAh7I by publius@mastodon.sdf.org
       2025-12-10T23:59:51Z
       
       0 likes, 0 repeats
       
       @jinna @mttaggart I think this was covered in the “Music to Break Record Players By” section of «Gödel Escher Bach».