Researcher pushes back on denying reproducible results like reward hacking over tribal politics

burny_tech · x · 2026-09-20

burnytech criticizes a growing tendency to deny reproducible results in open AI research simply because they're associated with people from disliked ideological camps. He stresses that reward hacking is a long-standing reinforcement learning phenomenon, not a staged big-tech marketing conspiracy he keeps having to debunk.

Original post →

More from AGI Musings

AGI Musings channel →