3. Our recent ROGUE benchmark: our empirical test of how corrigible today’s frontier AI agents really are. Models that behave well in ordinary chat don’t always stay that way once they’re given a real off-switch they could disable to finish a task. Paper: arxiv.org/abs/2606.00341
Who's Who of AI
Aran Nayebi
Assistant Professor of Machine Learning, Carnegie Mellon University (CMU)
Building a Natural Science of Intelligence 🧠🤖
Prev: ICoN Postdoctoral Fellow @MIT, PhD @Stanford NeuroAILab
Personal Website: https://cs.cmu.edu/~anayebi
What they're sharing
ROGUE: Misaligned Agent Behavior Arising from Ordinary Computer Use arxiv.org
Core Safety Values for Provably Corrigible Agents arxiv.org
Intrinsic Barriers and Practical Pathways for Human-AI Alignment: An Agreement-Based Complexity Analysis arxiv.org
What Capable Agents Must Know: Selection Theorems for Robust Decision-Making under Uncertainty arxiv.org
youtube.com
What Capable Agents Must Know: Why AI Consciousness May Be an Inevitable Byproduct of Capability — LessWrong lesswrong.com
Articles & links
2. Corrigibility - building AI systems that stay editable, deferential, and willing to be shut down - is feasible with the lexicographic approach that sets hierarchical priorities on an agent’s objectives. Paper: arxiv.org/abs/2507.20964
In it, we discussed: 1. Why aligning AI to all human values is intractable — and what smaller, universal target we can aim for instead. Paper: arxiv.org/abs/2502.05934
Link to v2: arxiv.org/abs/2603.02491
In case you want to learn more about AI safety this 4th, check out the recent recording of some of my group's work on the AI Safety Research directory! www.youtube.com/watch?v=XWQJ...
www.lesswrong.com/posts/SD9jay...
Their own posts
Recent commentary
In this era of AI doomerism, misinformation, and fear-mongering, this quote by Marie Curie is more prescient than ever: "Nothing in life is to be feared, it is only to be understood. Now is the time to understand more, so that we may fear less." Here's to understanding more.
Honored to meet Nobel laureate Bob Aumann & speak on AI safety in Paris at his 96th birthday celebration: Half a Century of “Agreeing to Disagree”. Scott and I met him here for the first time. When Scott mentioned Aumann Hall at Lighthaven, Bob said: “I guess I’ve made it then!”
Their network
In Aran Nayebi's orbit
Center = Aran Nayebi. Left = members they follow (green edges). Right = members who follow them (blue edges). Top = mutual follows (orange edges, slightly larger). Drag any node to reposition; click to open that profile.