Deceptive Alignment

Applied to What’s the short timeline plan? by Marius Hobbhahn 17h ago

Applied to Corrigibility's Desirability is Timing-Sensitive by RobertM 7d ago

Applied to AIs Will Increasingly Fake Alignment by Ruben Bloom 10d ago

Applied to Has Anthropic checked if Claude fakes alignment for intended values too? by Maloew 11d ago

Applied to “Alignment Faking” frame is somewhat fake by Jan_Kulveit 14d ago

Applied to Measuring whether AIs can statelessly strategize to subvert security measures by Alex Mallen 14d ago

Applied to Takes on "Alignment Faking in Large Language Models" 15d ago

Applied to Alignment Faking in Large Language Models by Ryan Greenblatt 16d ago

Applied to Ablations for “Frontier Models are Capable of In-context Scheming” by AlexMeinke 16d ago

Applied to Densing Law of LLMs by Bogdan Ionut Cirstea 26d ago

Applied to Backdoors have universal representations across large language models by Amirali Abdullah 1mo ago

Applied to Frontier Models are Capable of In-context Scheming by Marius Hobbhahn 1mo ago

Applied to AXRP Episode 39 - Evan Hubinger on Model Organisms of Misalignment by DanielFilan 1mo ago

Applied to LLMs Do Not Think Step-by-step In Implicit Reasoning by Bogdan Ionut Cirstea 1mo ago

Applied to Do Large Language Models Perform Latent Multi-Hop Reasoning without Exploiting Shortcuts? by Bogdan Ionut Cirstea 1mo ago

Applied to Training AI agents to solve hard problems could lead to Scheming by Marius Hobbhahn 1mo ago

Applied to Toward Safety Cases For AI Scheming by Mikita Balesni 2mo ago