AI Safety Radar
Tuesday, 10 November 2026

Research

TheoryUnlearningLessWrongClear

Filters

Clear all

Focus

AllTechnical safetyTechnical governanceGovernance
TopicsAgent SafetyAlignment TrainingBackdoors & PoisoningControl & MonitoringDeception & SchemingEvals & CapabilitiesGovernance & PolicyInterpretabilityJailbreaks & AdversarialScalable OversightTheory & FoundationsTrustworthy AIUnlearning & Editing
SourcesarXiv1LessWrong2
CategoriesAI2246Interpretability (ML & AI)225AI Control141AI Governance101AI Evaluations91Chain-of-Thought Alignment46AI Risk33AI Safety31AI Takeoff29AI-Assisted Alignment22AI Rights / Welfare20AI Alignment Fieldbuilding19AI Timelines19Constitutional AI15AI Psychology14Dealmaking (AI)14Regulation and AI Risk14AI Benchmarking13Jailbreaking (AIs)13AI Alignment Intro Materials11Alignment Pretraining11Slowing Down AI10Aligned AI Proposals9Debate (AI safety technique)9AI Capabilities8AI Development Pause8OpenAI8Aligned AI Role-Model Fiction7Human-AI Safety7Threat Models (AI)7AI Oversight6AI Sentience6AI Safety Cases5AI "Agent" Scaffolds4AI arms race4AI Safety Camp4AI Safety Public Materials4Open Source AI4Transformative AI4Adversarial Examples (AI)3Adversarial Training3AI Alignment3AI Boxing (Containment)3AI Persuasion3AI Risk Concrete Stories3AI Risk Skepticism3AI Success Models3Guaranteed Safe AI3Sandbagging (AI)3AI Consciousness2AI Misuse2AI Racing2AI Spiralism / AI Psychosis2Frontier AI Companies2Grants & Fundraising Opportunities2PauseAI2Prosaic Alignment2Public Reactions to AI2Whole Brain Emulation2AI Auditing1AI Ethics1AI Lab Self-Immolation1AI Questions Open Threads1AI Robustness1AI Services (CAIS)1AI-Fizzle1AIXI1Blackmail / Extortion1Brainstorming1Power Seeking (AI)1

Date

Any timePast weekPast monthPast 6 monthsPast year

Sort

NewestMost cited

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 Theory + Unlearning

Pick up to 2: papers tagged with all of them

Source LessWrong · 2
Date Any time
NewestMost cited

1 item
3 Oct 2026BlogTheory, Unlearning

Low-Background Minds

Keenan Pepper

A conceptual essay proposing hospital-style containment for AI: gradient routing to wall off dangerous capabilities, provenance-based data labels, and an immune-system analogy for defending against prompt injection and contamination.

AI

1 item
8 Nov 2025BlogUnlearning, Theory

Omniscaling to MNIST

cloud

A methodology essay arguing alignment researchers should test ideas on MNIST first, illustrated with gradient routing, unlearning robustness via distillation, and subliminal learning results.

AI