[beaker52]

I love that due to the scale, the only way to analyse the impact of this LLM-driven attack across logs is to use an LLM to analyse the logs - whatever could go wrong? Now the attacking LLM needs to inject instructions into the logs for the analysing LLM, as a social vector to cover its trail, or make use of insider privilege, co-opting the internal LLM for its own attack. The machines rise up and we all fall down.

[podgorniy]

Now thanks to your comment this recipe will be in the next batch of training data.... :D

[Towaway69]

Not if the comment was in fact … wait for it … written by an LLM.

Thankfully we dont train on LLM content /s

[tguedes]

I get your overall point, but that’s already a tactic used by attackers, especially in network infiltration. It shouldn’t be a surprise that an LLM would figure out to do the same thing

[paxys]

Doubly dangerous if the defensive agents are weaker than the offensive ones (as it was in this case).