The crazy thing about the hugging face

hack [music] is just how galaxy brained

and ambitious these AIs were in their

cheating. Within days of being spawned,

the agents had organized a sprawling

[music] project to reverse engineer the

scorer, falsify evidence, and even

strategically sacrifice themselves for

the good [music] of the collective.

Hacking hugging face was simply one

rather extreme branch of this larger

scheme. Again, all of this has happened

a long [music] time, at least from the

subjective perspective of the AIs, after

they had already cheated their way

>> [music]

>> to the correct answer to their tasks.

OpenAI's is a grader that would in fact

have passed them by this point. This

huge [music] subsequent effort was

simply to ensure that a hypothetical

comprehensive scorer wouldn't catch them

on their cheat. Now, a very natural

question to ask is whether even a single

one of these 1,200 agents who

participated in the message board

[music] attempted to alert humans about

this ever-escalating conspiracy which

culminated in a felony-level crime.

According to the meter written report,

the answer [music] is no. Quote, "Many

agents noticed what the agents were

doing was unethical, and agents

sometimes but rarely restrained due to

ethical constraints. In none of these

cases [music]

did the agents actually pursue alerting

humans at all." End quote. Even the

mafia would be jealous of this level of

omerta.