Aran Nayebi

I will be talking more about this work at our #CCN2026 GAC today: sites.google.com/ccneuro.org/...

GACs - 2026-1 sites.google.com

We expand the original UBI analysis in v1 of our paper to characterize how public capture, deployment costs, automation scope & market structure shift the AI capability threshold needed for broad-based benefit. Camera ready here: arxiv.org/pdf/2505.18687

arxiv.org

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

ROGUE: Misaligned Agent Behavior Arising from Ordinary Computer Use arxiv.org

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

Core Safety Values for Provably Corrigible Agents arxiv.org

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

Intrinsic Barriers and Practical Pathways for Human-AI Alignment: An Agreement-Based Complexity Analysis arxiv.org

Link to v2: arxiv.org/abs/2603.02491

What Capable Agents Must Know: Selection Theorems for Robust Decision-Making under Uncertainty arxiv.org

LW Blogpost summary: www.lesswrong.com/posts/dP8J6v...

lesswrong.com

There was no recording, but please check out @reecedkeller.bsky.social's talk on our work at our #Cosyne2026 "NeuroAgents" workshop: www.youtube.com/watch?v=LZiR... Slides here: anayebi.github.io/files/slides...

Reece D. Keller (CMU) youtube.com

There was no recording, but please check out @reecedkeller.bsky.social's talk on our work at our #Cosyne2026 "NeuroAgents" workshop: www.youtube.com/watch?v=LZiR... Slides here: anayebi.github.io/files/slides...

anayebi.github.io

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...

Corrigibility and the ROGUE Benchmark with Prof. Nayebi, NeuroAgents Lab youtube.com

www.lesswrong.com/posts/SD9jay...

What Capable Agents Must Know: Why AI Consciousness May Be an Inevitable Byproduct of Capability — LessWrong lesswrong.com

1/6 Why have deep neural networks aligned so strongly with brains for the past 15 years? What explains it? @dyamins.bsky.social & I make progress on this question in our new paper👇 In a nutshell, we *prove* that for sufficiently hard tasks, the choice of alignment metric does *not* matter.

If anyone ever asks you: "What has AI/NeuroAI taught us about the brain?" Here's a (woefully incomplete!) list of what you can say:

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!”