# Where does the race to automate AI research end?

> Source: <https://www.lesswrong.com/posts/gkbet5Gp7eoAE9bjY/where-does-the-race-to-automate-ai-research-end>
> Published: 2026-06-02 17:21:20+00:00

This is a linkpost of a recording of a recent MATS research talk where I argue that the automation of AI research — which OpenAI and Anthropic say is imminent — could lead to an unrecoverable alignment failure. Three properties make it especially dangerous: oversight breaks down at scale, capabilities self-amplify, and capabilities will be sped up asymmetrically faster than alignment. The outcome could be a lethal, unrecoverable alignment failure. [Link to the paper preprint](https://storage.googleapis.com/papers-preprint-simonlermen/rsi_paper_preprint.pdf).