Position: The Alignment Community is Unintentionally Building a Censor's Toolkit

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

<!-- 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

arXiv:2606.13755v1 Announce Type: cross Abstract: We argue that aligning AI to aggregated human preferences is the wrong target. With current technology, one can train AIs to

arXiv:2607.18263v1 Announce Type: new Abstract: AI-generated non-consensual intimate imagery (AIG-NCII) is not adequately addressed in AI/ML literature regarding AI-generated

arXiv:2607.22305v1 Announce Type: new Abstract: Pluralistic value alignment---the goal of building AI systems that represent and serve diverse human values and perspectives---has

arXiv:2604.26167v1 Announce Type: cross Abstract: Recent work has shown that a model's input word embeddings can serve as effective control variables for steering its behavior

arXiv:2607.05407v1 Announce Type: cross Abstract: Modern artificial intelligence (AI) systems present profound new risks to child safety. AI is increasingly being misused to