Intended goals reflect human operator desires even if poorly articulated, functioning as ideal ‘wishes’

Evidence

What is AI alignment? (TechTarget)

Categorization

• corroborated: 2 independent passages support this claim
• XREF: connects to: AI researchers aim to align general-purpose systems with hard-to-specify human intentions; Character is defined by desire and backward reasoning toward action. — Janet Burroway; Elizabeth Stuckey-French; Ned Stuckey-French, Writing Fiction, Tenth Edition: A Guide…, 251; Ethical rules for robots require human specifications of their key variables — Grégoire Chamayou, A Theory of the Drone, 676 (+1 more)

Related

• Intent-alignment doesn’t specify whose intentions matter, leaving trade-off conflicts unresolved (similarity 0.82)
• AI alignment may require machines to pursue human objectives, not their own (similarity 0.81)
• Ensuring AI captures human intent is now a central computer science problem (similarity 0.79)

Broader Connections

• Ethical rules for robots require human specifications of their key variables #corroborates (0.60) — Grégoire Chamayou, A Theory of the Drone, 676
• Automation requires active human work to organize the relinquishing of subjectivity #complicates (0.50) — Grégoire Chamayou, A Theory of the Drone, 650