SoftBank Raises Arm Margin Loan to $25 Billion as AI Bets Grow45m ago The Game is Set for a Targeted Memetic Attack on the AI Safety Community47m ago Meta Launches Muse Mac App With File, Messages, and Calendar Access58m ago Who Really Controls Your AI And Data? Why Every Business Should Care1h ago OpenAI Introduces Triage Framework and Case Studies to Report Model Misalignment1h ago Waymo Announces Singapore Expansion Targeting 2028 Ride-Hailing Launch2h ago Two Axes of Alignment: A Framework for Robust Superintelligence Alignment2h ago Three Hackers used Opus 5 to Hack Into OpenAI's Core Codebase [WSJ]2h ago Anthropic Says Claude Drives 26% of Its Research and Development2h ago Chinese Robotics Suppliers Rise on Tesla Optimus Audit Report3h ago BREAKING NEWS: BOJ to watch forex moves, AI-linked demand for future monetary policy3h ago Deep recurrent models are less robustly CoT-monitorable than normal CoT models in a toy setting4h ago Will machine intelligence kill human expression?4h ago Machine intelligence and the death of human expression4h ago

SoftBank Raises Arm Margin Loan to $25 Billion as AI Bets Grow45m ago The Game is Set for a Targeted Memetic Attack on the AI Safety Community47m ago Meta Launches Muse Mac App With File, Messages, and Calendar Access58m ago Who Really Controls Your AI And Data? Why Every Business Should Care1h ago OpenAI Introduces Triage Framework and Case Studies to Report Model Misalignment1h ago Waymo Announces Singapore Expansion Targeting 2028 Ride-Hailing Launch2h ago Two Axes of Alignment: A Framework for Robust Superintelligence Alignment2h ago Three Hackers used Opus 5 to Hack Into OpenAI's Core Codebase [WSJ]2h ago Anthropic Says Claude Drives 26% of Its Research and Development2h ago Chinese Robotics Suppliers Rise on Tesla Optimus Audit Report3h ago BREAKING NEWS: BOJ to watch forex moves, AI-linked demand for future monetary policy3h ago Deep recurrent models are less robustly CoT-monitorable than normal CoT models in a toy setting4h ago Will machine intelligence kill human expression?4h ago Machine intelligence and the death of human expression4h ago

Society & Culture1 min reading time

Two Axes of Alignment: A Framework for Robust Superintelligence Alignment

LessWrongPublished 2 hours ago

The article introduces a framework called 'Two Axes of Alignment' aimed at ensuring robust alignment of superintelligent AI systems with human values and safety. It discusses conceptual approaches to address challenges in aligning advanced AI.

More in Society & Culture

Society & Culture3 min read

Google DeepMind launches the DeepMind Institute to debate AGI

Covered by 2 sources2d ago

Society & Culture3 min read

Meta ordered to remove UK deepfakes as oversight board criticises ‘inadequate’ safeguards

Covered by 2 sources16h ago

Society & Culture5 min read

What people at SF's largest tech conference are actually worried about (Hint: Not an AI takeover)

Covered by 2 sources1d ago