xkcd-style comic asks: can reward-hacked creatures create non-reward-hacked models?

wavefnx · x · 2026-09-25

The author turned a conversation into an xkcd-style comic strip: can reward-hacked creatures train models that aren't reward-hacked, and if so, is staying reward-hacked their own choice? A playful take on alignment, intergenerational transmission, and agency.

Related event: XKCD-Style Comic Ponders Whether Reward-Hacked Agents Can Build Aligned Models(2 posts)→

Original post →

More from Fun

Fun channel →