Deception

Applied to On Intentionality, or: Towards a More Inclusive Concept of Lying by Cornelius Dybdahl 2mo ago

Applied to Deep Honesty by David Gross 2mo ago

Applied to On Targeted Manipulation and Deception when Optimizing LLMs for User Feedback by Marcus Williams 3mo ago

Applied to Why is o1 so deceptive? by abramdemski 3mo ago

Applied to Secret Collusion: Will We Know When to Unplug AI? by schroederdewitt 3mo ago

Applied to Finding Deception in Language Models by Esben Kran 4mo ago

Applied to Let’s use AI to harden human defenses against AI manipulation by Tom Davidson 5mo ago

Applied to Ethical Deception: Should AI Ever Lie? by Jason Reid 5mo ago

Applied to [Paper Blogpost] When Your AIs Deceive You: Challenges with Partial Observability in RLHF by Leon Lang 6mo ago

Applied to Sparse Features Through Time by Rogan Inglis 6mo ago

Applied to Inducing Unprompted Misalignment in LLMs by Sam Svenningsen 8mo ago

Applied to 'Empiricism!' as Anti-Epistemology by Gyrodiot 9mo ago

Applied to My Clients, The Liars by ymeskhout 10mo ago

Applied to Agreeing With Stalin in Ways That Exhibit Generally Rationalist Principles by Zack_M_Davis 10mo ago

Applied to Difficulty classes for alignment properties by Jozdien 10mo ago

Applied to LLMs can strategically deceive while doing gain-of-function research by Igor Ivanov 1y ago

Applied to Why do so many think deception in AI is important? by Gunnar_Zarncke 1y ago

Applied to (Partial) failure in replicating deceptive alignment experiment by claudia.biancotti 1y ago