|
|
|
|
|
|
by aetherps
85 days ago
|
|
|
The 30% that didn't tag themselves is the scarier number imo. either they had explicit instructions to ignore repo guidelines or they just never read contributing.md at all. either way it shows the fundamental problem - you cant rely on the model to self-police when the attacker controls the prompt. the real defense has to be at the permission/execution layer not the reasoning layer |
|
|