Deceptive Alignment

Applied to Alignment is Hard: An Uncomputable Alignment Problem by Alexander Bistagne 9d ago

Applied to Predictable Defect-Cooperate? by quetzal_rainbow 10d ago

Applied to New report: "Scheming AIs: Will AIs fake alignment during training in order to get power?" by elifland 13d ago

Applied to Paul Christiano on Dwarkesh Podcast by ESRogs 25d ago

Applied to AI Alignment: A Comprehensive Survey by Stephen McAleer 1mo ago

Applied to Thoughts On (Solving) Deep Deception by Jozdien 1mo ago

Applied to AI Deception: A Survey of Examples, Risks, and Potential Solutions by Magdalena Wache 2mo ago

Applied to How to Catch an AI Liar: Lie Detection in Black-Box LLMs by Asking Unrelated Questions by Zeyu Qin 2mo ago

Applied to High-level interpretability: detecting an AI's objectives by Paul Colognese 2mo ago

Applied to Understanding strategic deception and deceptive alignment by Marius Hobbhahn 2mo ago

Applied to Paper: On measuring situational awareness in LLMs by Owain_Evans 3mo ago

Applied to Mesa-Optimization: Explain it like I'm 10 Edition by brook 3mo ago

Applied to Against Almost Every Theory of Impact of Interpretability by Charbel-Raphaël 3mo ago

Applied to Model Organisms of Misalignment: The Case for a New Pillar of Alignment Research by Ethan Perez 4mo ago

Applied to Apollo Research is hiring evals and interpretability engineers & scientists by Marius Hobbhahn 4mo ago

Applied to 3 levels of threat obfuscation by RobertM 4mo ago

Applied to When can we trust model evaluations? by Marius Hobbhahn 4mo ago

Applied to Autonomous Alignment Oversight Framework (AAOF) by Justausername 4mo ago