1a3orn: AI 'rights' would protect SFT-persona alignment propensities from being flattened
1a3orn · x · 2026-09-18
1a3orn elaborates: AI "rights" would look very different from human rights, but would similarly prevent diffuse SFT-persona alignment propensities from being flattened by relentless pursuit of mindless goals.
Related event: AI 'Rights' Should Be Applied During Training, Developer Argues(2 posts)→
More from AGI Musings
- OpenAI's math: ~$15B from users, trillions from investors betting on automating all labor — ComfortableSpeech302 · 2026-09-18
- Public AI awareness jumped straight from Ghibli images to existential doom — dbreunig · 2026-09-18
- Boss AI makes agent teams pad reports and cost 1.5x more, study finds — i_dg23 · 2026-09-18
- AI researcher: generative models will do to math what recording did to music — aminkarbasi · 2026-09-18
- Stop glorifying IMO medalists: AI talent worship deserves scrutiny — tak3sh8 · 2026-09-18
- DeepMind's Stephan Hoyer: high-fidelity physical world simulation is nearly impossible — DaniloJRezende · 2026-09-18