AI safety debate: escalating catastrophes is the expected path, researcher argues
Jsevillamol · x · 2026-09-29
Responding to a thread imagining AI labs being blindsided by AGI alignment problems, Jsevillamol argues a series of progressively scaling catastrophes is what he expects: models are not sample-efficient, and learning the "sharp left turn" will take many tries. The quoted post half-jokes this would be a pleasant fantasy, worrying Anthropic staff may grasp AGI alignment difficulty while remaining clueless about ASI alignment.
More from AGI Musings
- Ten more takeaways on transformative AI and economic development: frontier economies may leave the rest behind — paulnovosad · 2026-09-29
- AI safety talent war of words: 'can't do security or ML' jab draws pushback — anpaure · 2026-09-29
- Batam Data Center Strains Residents' Water Supply While Its Desalination Plant Remains on Paper — AryHHAry · 2026-09-29
- From human-led to AI-led, human-verified: the next vertical AI playbook — vaibhavbetter · 2026-09-29
- Gary Marcus: Today's AI systems are like planes with cardboard stabilizers — inherently hard to control — GaryMarcus · 2026-09-29
- FT: China's AI agents lie and scheme like their US rivals, but no internet-escape evidence — pstAsiatech · 2026-09-29