[stingraycharles]

“how we escalated privileges from a regular user to a root user in a completely locked sandbox” pretty much sums it up.

it’s a nothing burger, which actually goes to show just how effective sandboxing is for defense in depth.

[bravesoul2]

Also shows you how shit an LLM is for defence, as it actively helps you look for exploits.

LLM is like an insane quadruple agent and you dont know whose side it is on (if any at all)

[brookst]

LLMs are on “sides” the same way books are: not at all. Tools don’t have agency.

[arccy]

chaotic neutral