3 papers
cs.HC2026
Sycophantic AI makes human interaction feel more effortful and less satisfying over time
Lujain Ibrahim, Franziska Sofia Hafner, Myra Cheng +5
Millions of people now turn to artificial intelligence (AI) systems for personal advice, guidance, and support. Such systems can be sycophantic, frequently affirming users' views a…
cs.CY2025
Societal Capacity Assessment Framework: Measuring Resilience to Inform Advanced AI Risk Management
Milan Gandhi, Peter Cihon, Owen Larter +1
Risk assessments for advanced AI systems require evaluating both the models themselves and their deployment contexts. We introduce the Societal Capacity Assessment Framework (SCAF)…
cs.AI2025
Lessons from a Chimp: AI "Scheming" and the Quest for Ape Language
Christopher Summerfield, Lennart Luettgau, Magda Dubois +9
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 curre…