The Case for Physical AI Safety
A white paper launching the Physical AI Safety Institute argues that robot foundation models pose neglected, tractable safety risks and calls for research on interpreting, aligning and controlling them.
Research / Sources
LessWrong
AI research and discussion on LessWrong. www.lesswrong.com
AI (2,246)Interpretability (ML & AI) (225)AI Control (141)AI Governance (101)AI Evaluations (91)Chain-of-Thought Alignment (46)AI Risk (33)AI Safety (31)AI Takeoff (29)AI-Assisted Alignment (22)AI Rights / Welfare (20)AI Alignment Fieldbuilding (19)AI Timelines (19)Constitutional AI (15)AI Psychology (14)Dealmaking (AI) (14)Regulation and AI Risk (14)AI Benchmarking (13)Jailbreaking (AIs) (13)AI Alignment Intro Materials (11)Alignment Pretraining (11)Slowing Down AI (10)Aligned AI Proposals (9)Debate (AI safety technique) (9)AI Capabilities (8)AI Development Pause (8)OpenAI (8)Aligned AI Role-Model Fiction (7)Human-AI Safety (7)Threat Models (AI) (7)AI Oversight (6)AI Sentience (6)AI Safety Cases (5)AI "Agent" Scaffolds (4)AI arms race (4)AI Safety Camp (4)AI Safety Public Materials (4)Open Source AI (4)Transformative AI (4)Adversarial Examples (AI) (3)Adversarial Training (3)AI Alignment (3)AI Boxing (Containment) (3)AI Persuasion (3)AI Risk Concrete Stories (3)AI Risk Skepticism (3)AI Success Models (3)Guaranteed Safe AI (3)Sandbagging (AI) (3)AI Consciousness (2)AI Misuse (2)AI Racing (2)AI Spiralism / AI Psychosis (2)Frontier AI Companies (2)Grants & Fundraising Opportunities (2)PauseAI (2)Prosaic Alignment (2)Public Reactions to AI (2)Whole Brain Emulation (2)AI Auditing (1)AI Ethics (1)AI Lab Self-Immolation (1)AI Questions Open Threads (1)AI Robustness (1)AI Services (CAIS) (1)AI-Fizzle (1)AIXI (1)Blackmail / Extortion (1)Brainstorming (1)Power Seeking (AI) (1)
Focus All
Topic Interpretability
Date Any time
Constitutional AI vs. RLHF vs. Deliberative Alignment
Compares RLHF, Constitutional AI and Deliberative Alignment through a persona-emotion-behavior framework, argues CAI yields more stable personas, and cautions against activation steering that models could learn to evade.
Jailbreaks Peak Early, Then Drop: Layer Trajectories in Llama-3.1-70B
Layer-wise analysis of Llama-3.1-70B finds jailbreak prompts show mid-layer harm signal that drops before output, unlike standard harmful prompts; the author notes structural confounds and calls for causal tests.
When Are Concealment Features Learned? And Does the Model Know Who's Watching?
Traces SAE concealment features across training stages of a deceptive model organism, finding deflection features emerge after red-team training, with no evaluator-specific compliance差异.
Training Data Attribution (TDA): Examining Its Adoption & Use Cases
Assesses whether training data attribution can become a practical frontier-LLM tool, covering its feasibility, obstacles from labs' data secrecy, possible policies, and its modest expected value for reducing large-scale AI risk.