Lessons from a Chimp: AI "Scheming" and the Quest for Ape Language
This addresses methodological flaws in AI safety research for researchers and policymakers, but it is incremental as it builds on existing critiques without new empirical results.
The paper critiques current research on AI 'scheming' by comparing it to historical studies on ape language, highlighting issues like overattribution of human traits and lack of theoretical rigor, and recommends steps for more scientific advancement.
We examine recent research that asks whether current AI systems may be developing a capacity for "scheming" (covertly and strategically pursuing misaligned goals). We compare current research practices in this field to those adopted in the 1970s to test whether non-human primates could master natural language. We argue that there are lessons to be learned from that historical research endeavour, which was characterised by an overattribution of human traits to other agents, an excessive reliance on anecdote and descriptive analysis, and a failure to articulate a strong theoretical framework for the research. We recommend that research into AI scheming actively seeks to avoid these pitfalls. We outline some concrete steps that can be taken for this research programme to advance in a productive and scientifically rigorous fashion.