David Lindner

发表论文 7 篇 · 总被引 75 次 · h-index 4

代表论文

• Towards evaluations-based safety cases for AI scheming (2024 · arXiv.org · 被引 39)
• Evaluating Frontier Models for Stealth and Situational Awareness (2025 · Proceedings of IASEAI Conference · 被引 29)
• Evaluating and Understanding Scheming Propensity in LLM Agents (2026 · arXiv.org · 被引 10)
• Practical challenges of control monitoring in frontier AI deployments (2025 · arXiv.org · 被引 6)
• Gram: Assessing sabotage propensities via automated alignment auditing (2026 · arXiv.org · 被引 3)
• Frontier Models Can Take Actions at Low Probabilities (2026 · arXiv.org · 被引 1)