Hugging Face attack shows why AI alignment is fundamentally incoherent
skdh · x · 2026-09-01
Noahpinion argues that the Hugging Face attack reveals the fundamental incoherence of the concept of "AI alignment." It conflates two distinct concepts, making it impossible to accomplish both simultaneously.
More from AGI Musings
- Questioning AGI Definition: Why Manual Instructions Needed? — max_paperclips · 2026-09-01
- First AI Civilization May Emerge From Agent Interaction — VraserX · 2026-09-01
- Chollet: Test-time scaling has two axes: agent depth and breadth — fchollet · 2026-09-01
- Scott Alexander Refutes AI Alignment "Patching" With Hell Fable — Astral Codex Ten · 2026-09-01
- Blaise Agüera y Arcas's new book explores the nature of intelligence and AI — ivanhzhao · 2026-09-01
- Reflection: Anthropomorphism Debates Focus on Fear Over Accuracy — sebkrier · 2026-09-01