activity
20172026
most citedAI Safety Gridworlds

117 citations · 263 across the 17 of their papers we have counts for

collaborators

14 papers

cs.AI2026

AI Finds A Way

Aaron Dharna, Cong Lu, Ryan Sullivan +3

Artificial Intelligence (AI) algorithms frequently learn creative and unexpected solutions, surprising even expert researchers who develop and study them. They often astonish pract…

cs.AI2026

Persuasion Attacks Can Decrease Effectiveness of CoT Monitoring

Jennifer Za, Julija Bainiaksina, Nikita Ostrovsky +2

Chain-of-thought (CoT) monitoring is a promising safety mechanism for AI agents, based on the premise that visible reasoning traces can surface misaligned or deceptive behavior. Wh…

cs.LG2026

Realistic honeypot evaluations for scheming propensity

Victoria Krakovna, David Lindner, Lewis Ho +2

We introduce scheming honeypot evaluations, a framework for testing whether models will pursue instrumental goals if given the opportunity. Our scheming honeypot evaluations take t…

cs.AI2025

Chain of Thought Monitorability: A New and Fragile Opportunity for AI Safety

Tomek Korbak, Mikita Balesni, Elizabeth Barnes +38

AI systems that "think" in human language offer a unique opportunity for AI safety: we can monitor their chains of thought (CoT) for the intent to misbehave. Like all other known A…

cs.CL2025

Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities

Gheorghe Comanici, Eric Bieber, Mike Schaekermann +3431

In this report, we introduce the Gemini 2.X model family: Gemini 2.5 Pro and Gemini 2.5 Flash, as well as our earlier Gemini 2.0 Flash and Flash-Lite models. Gemini 2.5 Pro is our…

cs.LG2025

Evaluating Frontier Models for Stealth and Situational Awareness

Mary Phuong, Roland S. Zimmermann, Ziyue Wang +6

Recent work has demonstrated the plausibility of frontier AI models scheming -- knowingly and covertly pursuing an objective misaligned with its developer's intentions. Such behavi…