# Instrumental convergence and power-seeking

arXiv: https://arxiv.org/abs/2606.08832 · HTML: https://mlsanity.com/paper/2606.08832/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 38 references that are in the map.
- First posted on arXiv 7 Jun 2026.

## Builds on (most cited first, 9 of 9)

- [The Effects of Reward Misspecification: Mapping and Mitigating Misaligned Models](https://mlsanity.com/paper/2201.03544/) (2022)
- [Scaling Monosemanticity: Extracting Interpretable Features from Claude 3 Sonnet](https://mlsanity.com/paper/2605.29358/) (2026)
- [Goal Misgeneralization: Why Correct Specifications Aren't Enough For Correct Goals](https://mlsanity.com/paper/2210.01790/) (2022)
- [Optimal Policies Tend to Seek Power](https://mlsanity.com/paper/1912.01683/) (2019)
- [Is Power-Seeking AI an Existential Risk?](https://mlsanity.com/paper/2206.13353/) (2022)
- [Auditing Radicalization Pathways on YouTube](https://mlsanity.com/paper/1908.08313/) (2019)
- [Power-seeking can be probable and predictive for trained agents](https://mlsanity.com/paper/2304.06528/) (2023)
- [Deception and Manipulation in Generative AI](https://mlsanity.com/paper/2401.11335/) (2024)
- [Future progress in artificial intelligence: A survey of expert opinion](https://mlsanity.com/paper/2508.11681/) (2025)

## Abstract (arXiv)

Recent years have seen increasing concern that artificial intelligence may soon pose an existential risk to humanity. One leading ground for concern is that artificial agents may be power-seeking, aiming to acquire power and in the process disempowering humanity. I show how the argument from power-seeking rests on a strong version of a claim known as the instrumental convergence thesis. I explore leading defenses of the instrumental convergence thesis and argue that none establishes the thesis in a strong enough form to ground the argument from power-seeking. I discuss implications for longtermism, the governance of artificial intelligence, and the methodology of studying risks posed by artificial agents.