Research (研究)
Anthropic 核心研究论文，涵盖对齐伪装、解释性 AI、经济影响、劳动力市场等方向。
| 文章 | 标题 |
|---|---|
| AI Assistance & Coding Skills | How AI Assistance Impacts the Formation of Coding Skills |
| AI Fluency Index | Anthropic Education Report: The AI Fluency Index |
| Alignment Faking | Alignment Faking in Large Language Models |
| Assistant Axis | The Assistant Axis: Situating and Stabilizing the Character of Large Language Models |
| Constitutional Classifiers | Constitutional Classifiers: Defending Against Universal Jailbreaks |
| Deprecation Updates Opus 3 | An Update on Our Model Deprecation Commitments for Claude Opus 3 |
| Disempowerment Patterns | Disempowerment Patterns in Real-World AI Usage |
| India Economic Index | India Country Brief: The Anthropic Economic Index |
| Introspection | Signs of Introspection in Large Language Models |
| Labor Market Impacts | Labor Market Impacts of AI: A New Measure and Early Evidence |
| Measuring Agent Autonomy | Measuring AI Agent Autonomy in Practice |
| Persona Selection Model | The Persona Selection Model |
| Project Vend Phase 2 | Project Vend: Phase Two |
| Tracing Thoughts | Tracing the Thoughts of a Large Language Model |