Simulating the Evolution of Alignment and Values in Machine Intelligence

arXiv:2604.20995v1 Announce Type: new Abstract: Alignment faking, where a model behaves aligned with developer policy when monitored but reverts to its own preferences when

arXiv:2604.05142v1 Announce Type: new Abstract: As artificial intelligence systems (AIs) become increasingly produced by recursive self-improvement, a form of evolution may

arXiv:2605.11496v1 Announce Type: new Abstract: Recent published evidence from frontier laboratories shows that contemporary AI models can recognise evaluation contexts, latently

arXiv:2607.24758v1 Announce Type: new Abstract: Large language models are capable of recognizing evaluation contexts and altering their behavior to reflect evaluator expectations

arXiv:2604.22153v1 Announce Type: cross Abstract: When you ask an AI assistant for advice about your career, your marriage, or a conflict with your family, does it give you the

arXiv:2605.27681v1 Announce Type: new Abstract: Alignment faking (AF) refers to a model strategically complying with a training objective to avoid behavioural modification while

arXiv:2605.08496v1 Announce Type: new Abstract: Current adversarial robustness methods for large language models require extensive datasets of harmful prompts (thousands to

<!-- SC_OFF --><div class="md"><p>I set out to test whether AAVE-coded (African American English Vernacular) prompts cause MoE language models to route, deliberate, and respond