Research / Sources
AI research and discussion on LessWrong. www.lesswrong.com
Argues that common theories of change for surviving ASI fail under race dynamics, covering nuclear war, misaligned AI, and nightmare singletons, and that safety work can boost capabilities, so international coordination is needed.
Proposes borrowing coverage-driven verification from autonomous-vehicle testing to systematically train and evaluate alignment, using explicit coverage maps over scenario dimensions for long-horizon AI agents; largely a conceptual proposal without empirical results.
Argues that LLMs can now load human intent and values, so alignment is tractable but unsolved, citing InstructGPT, Constitutional AI, and emergent misalignment results.
Sketches a realistic target future where superintelligent AI stays under permanent human control through dynamic alignment targets, structured multi-source feedback, and institutional norms, without claiming a technical solution.
AE Studio argues alignment techniques can boost capabilities, so alignment is a competitive advantage, and urges US policymakers to fund neglected alignment research and adopt incentives for it.