Joshua Clymer

发表论文 11 篇 · 总被引 273 次 · h-index 7

代表论文

• RE-Bench: Evaluating frontier AI R&D capabilities of language model agents against human experts (2024 · arXiv.org · 被引 151)
• Safety Cases: How to Justify the Safety of Advanced AI Systems (2024 · arXiv.org · 被引 73)
• Towards evaluations-based safety cases for AI scheming (2024 · arXiv.org · 被引 39)
• A sketch of an AI control safety case (2025 · arXiv.org · 被引 35)
• Poser: Unmasking Alignment Faking LLMs by Manipulating Their Internals (2024 · arXiv.org · 被引 12)
• Affirmative safety: An approach to risk management for high-risk AI (2024 · arXiv.org · 被引 12)