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.
More from AGI Musings
- Abnormal AI founder: AI-savvy builders gain 2-10x, fear-driven resisters will lose — bindureddy · 2026-09-20
- Calibration is all you need: trustworthy probabilities beat confident predictions — zsakib_ · 2026-09-20
- Researcher mocks doom numbers: I give 10% odds of human extinction if we pause frontier AI — JJitsev · 2026-09-20
- Pedro Domingos: The amount of compute wasted on RL is mind-boggling — pmddomingos · 2026-09-20
- AI agent called customer service, navigated the phone tree and resolved the issue unnoticed — ziv_ravid · 2026-09-20
- When a Prompt Yields Publishable Work, How Should Journals Respond? — JJitsev · 2026-09-20