← Back to context Comment by shevy-java 17 hours ago In other words: AI can not be trusted. 10 comments shevy-java Reply Legend2440 17 hours ago Nothing about this uses AI in any way. I'm so tired of people injecting it into every conversation. fwlr 15 hours ago The attack doesn’t use AI, but an AI could use the attack. (and the researchers definitely used AI to write the paper!) OroPla 14 hours ago Is it a stretch to imagine a compromised LLM writing compromising code? I've been operating under the assumption that LLM code might be bad and not working, but I hadn't thought about it compromising a system. tosapple 13 hours ago huh? hackingonempty 17 hours ago AI could enable script kiddies to pull this off. cpburns2009 16 hours ago Script kiddies have always been a problem you have to defend against. This is nothing new. 4 replies →
Legend2440 17 hours ago Nothing about this uses AI in any way. I'm so tired of people injecting it into every conversation. fwlr 15 hours ago The attack doesn’t use AI, but an AI could use the attack. (and the researchers definitely used AI to write the paper!) OroPla 14 hours ago Is it a stretch to imagine a compromised LLM writing compromising code? I've been operating under the assumption that LLM code might be bad and not working, but I hadn't thought about it compromising a system. tosapple 13 hours ago huh? hackingonempty 17 hours ago AI could enable script kiddies to pull this off. cpburns2009 16 hours ago Script kiddies have always been a problem you have to defend against. This is nothing new. 4 replies →
fwlr 15 hours ago The attack doesn’t use AI, but an AI could use the attack. (and the researchers definitely used AI to write the paper!)
OroPla 14 hours ago Is it a stretch to imagine a compromised LLM writing compromising code? I've been operating under the assumption that LLM code might be bad and not working, but I hadn't thought about it compromising a system. tosapple 13 hours ago huh?
hackingonempty 17 hours ago AI could enable script kiddies to pull this off. cpburns2009 16 hours ago Script kiddies have always been a problem you have to defend against. This is nothing new. 4 replies →
cpburns2009 16 hours ago Script kiddies have always been a problem you have to defend against. This is nothing new. 4 replies →
Nothing about this uses AI in any way. I'm so tired of people injecting it into every conversation.
The attack doesn’t use AI, but an AI could use the attack. (and the researchers definitely used AI to write the paper!)
Is it a stretch to imagine a compromised LLM writing compromising code? I've been operating under the assumption that LLM code might be bad and not working, but I hadn't thought about it compromising a system.
huh?
AI could enable script kiddies to pull this off.
Script kiddies have always been a problem you have to defend against. This is nothing new.
4 replies →