All Publications

Anthropic

Company BlogHigh(4)

AI safety company, Claude developer

Credibility Rating

4/5

High(4)

High quality. Established institution or organization with editorial oversight and accountability.

81

Resources

130

Citing pages

1

Tracked domains

Tracked Domains

anthropic.com

Resources (81)

81 resources

			Summary
Anthropic	web	-	S	38
Anthropic's Work on AI Safety	paper	-	S	36
Responsible Scaling Policy	web	-	S	14
Anthropic's 2024 alignment faking study	web	-	S	13
Anthropic's follow-up research on defection probes	web	-	S	12
Constitutional AI: Harmlessness from AI Feedback	paper	-	S	11
Anthropic's Core Views on AI Safety	web	-	S	7
Anthropic: Announcing our updated Responsible Scaling Policy	web	-	S	7
Anthropic safety evaluations	web	-	S	6
Anthropic's	web	-	S	5
Anthropic's Constitutional AI work	web	-	S	5
Collective Constitutional AI	paper	-	S	5
Anthropic's sleeper agents research (2024)	web	-	S	4
Anthropic system card	web	-	S	4
Anthropic pioneered the Responsible Scaling Policy	web	-	S	4
anthropic.com/research/team/interpretability	web	-	S	4
observations of strategic reasoning	web	-	S	3
Anthropic careers	web	-	S	3
Anthropic's research on sycophancy	web	-	S	3
Natural Emergent Misalignment from Reward Hacking	web	-	S	3
Claude's constitution	web	-	S	3
Claude	web	-	S	3
Constitutional AI: Anthropic	web	-	S	2
large language models	web	-	S	2
Anthropic research	web	-	S	2

Rows per page:

Page 1 of 4

Citing Pages (130)

AI Accident Risk Cruxes Agentic AI AGI Development AGI Timeline AI-Assisted Alignment AI Control AI Alignment Alignment Evaluations Alignment Robustness Trajectory Model Anthropic Anthropic Core Views Anthropic IPO Anthropic Pre-IPO DAF Transfers Anthropic Stakeholders Apollo Research Alignment Research Center Autonomous Weapons Escalation Model Bioweapons Risk AI Uplift Assessment Model Bioweapons Attack Chain Model Center for AI Safety Capabilities-to-Safety Pipeline Model Capability Elicitation AI Capability Threshold Model Carlsmith's Six-Premise Argument The Case For AI Existential Risk Autonomous Coding AI Compounding Risks Analysis Model AI-Driven Concentration of Power Constitutional AI Corrigibility Corrigibility Failure Corrigibility Failure Pathways Cyberweapons Risk Autonomous Cyber Attack Timeline Daniela Amodei Dario Amodei AI Safety via Debate Deceptive Alignment Deceptive Alignment Decomposition Model AI Safety Defense in Depth Model AI-Assisted Deliberation AI Disinformation AI Policy Effectiveness AI-Induced Enfeeblement Epistemic Sycophancy EU AI Act Eval Saturation & The Evals Gap AI Evaluation Evan Hubinger Goal Misgeneralization Goal Misgeneralization Probability Model Goal Misgeneralization Research AI Governance and Policy Heavy Scaffolding / Agentic Systems Holden Karnofsky AI-Human Hybrid Systems Instrumental Convergence Instrumental Convergence Framework Interpretability AI Safety Intervention Effectiveness Matrix AI Knowledge Monopoly AI Lab Safety Culture Large Language Models Large Language Models AI Value Lock-in Long-Horizon Autonomous Tasks Mechanistic Interpretability Mesa-Optimization Mesa-Optimization Risk Analysis Metaculus Machine Intelligence Research Institute AI Misuse Risk Cruxes AI Model Specifications Multipolar Trap Dynamics Model Open Source AI Safety OpenAI Optimistic Alignment Worldview Paul Christiano Pause Advocacy Should We Pause AI Development?Persuasion and Social Manipulation Power-Seeking AI Power-Seeking Emergence Conditions Model Pre-TAI Capital Deployment: $100B-$300B+ Spending Analysis Probing / Linear Probes AI Proliferation AI Development Racing Dynamics Racing Dynamics Impact Model Reasoning and Planning Red Teaming Redwood Research Responsible Scaling Policies (RSPs)Reward Hacking Reward Hacking Taxonomy and Severity Model AI Risk Activation Timeline Model AI Risk Cascade Pathways Model AI Risk Interaction Matrix AI Risk Interaction Network Model RLHF Responsible Scaling Policies AI Safety Culture Equilibrium Model AI Safety Research Allocation Model AI Safety Research Value Model AI Safety Researcher Gap Model AI Capability Sandbagging Sandboxing / Containment Scalable Oversight AI Scaling Laws Scheming Scheming & Deception Detection Scheming Likelihood Assessment Survival and Flourishing Fund Sharp Left Turn Situational Awareness Sleeper Agent Detection AI Safety Solution Cruxes State-Space Models / Mamba AI Model Steganography Structured Access / API-Only Sycophancy Sycophancy Feedback Loop Model AI Safety Technical Pathway Decomposition Technical AI Safety Research Treacherous Turn Voluntary AI Safety Commitments AI Risk Warning Signs Model Why Alignment Might Be Easy Why Alignment Might Be Hard Worldview-Intervention Mapping

Publication ID: anthropic

Anthropic | Publications | Longterm Wiki | Longterm Wiki