logoalt Hacker News

milkshakesyesterday at 11:26 PM1 replyview on HN

this is quite literally reward hacking. the model, under evaluation with cyber capabilities enabled, used those capabilities to simply bypass the exercise entirely and aim straight for the source of the flag. the CTF equivalent back in the day would be hacking the scoreboard.

in a street fight, the only rules are that there are no rules.


Replies

dannywtoday at 2:04 AM

this is more than reward hacking, this is actual reward HACKING ;)