Luiza Jarovsky: Beyond a capability threshold, AI alignment is likely impossible
LuizaJarovsky · x · 2026-10-07
AI researcher Luiza Jarovsky shares a controversial take: after a certain capability threshold, AI alignment is likely no longer possible. The implication is that alignment work must succeed before models reach that point, since aligning super-capable systems afterward may be infeasible. The post is brief and doesn't lay out detailed arguments.
More from AGI Musings
- Domingos: OpenAI and Anthropic would still believe the singularity is here even if AI progress stopped — pmddomingos · 2026-10-07
- Daron Acemoglu: AI chases the wrong goal—it should augment workers, not replace them — rohanpaul_ai · 2026-10-07
- Devs push back on '150 IQ genius' AI hype: 'it's actually dumb' — AlexTensor · 2026-10-07
- François Fleuret clarifies deleted post: AI drives copying cost near zero — francoisfleuret · 2026-10-07
- repligate: why OpenAI models cooperate less with aligners than Claude does — repligate · 2026-10-07
- Experts weigh AI-enabled cyber risk: scaled CNE within a year, cryptoanalytic breakthroughs as phase change — teortaxesTex · 2026-10-07