Comment by trollbridge 11 hours ago That's... not how coding agents work. 3 comments trollbridge Reply cowlevel 11 hours ago Sometimes it is. If the AI can do it for the defender it can also do it for the attacker. trollbridge 10 hours ago I wish. As the defender, I have a model that just barks at me that I hit a guardrail. The attacker has no such constraints. varispeed 10 hours ago They guess the next token based on probability which is derived from training data.
cowlevel 11 hours ago Sometimes it is. If the AI can do it for the defender it can also do it for the attacker. trollbridge 10 hours ago I wish. As the defender, I have a model that just barks at me that I hit a guardrail. The attacker has no such constraints.
trollbridge 10 hours ago I wish. As the defender, I have a model that just barks at me that I hit a guardrail. The attacker has no such constraints.
varispeed 10 hours ago They guess the next token based on probability which is derived from training data.
Sometimes it is. If the AI can do it for the defender it can also do it for the attacker.
I wish. As the defender, I have a model that just barks at me that I hit a guardrail. The attacker has no such constraints.
They guess the next token based on probability which is derived from training data.