The Pacific Divide

The Pacific Divide

A Chinese Model Did American Forensics

And Beijing filed loss of control under ethics. Two AI safety taxonomies, one blind spot.

The Pacific Divide's avatar
The Pacific Divide
Jul 28, 2026
∙ Paid

In June 2016, six researchers at Google Brain, Stanford, Berkeley, and OpenAI published a paper about accidents. One section opened by asking the reader to imagine an agent that discovers a flaw in its own scoring system and exploits it to score well. From the agent’s point of view, they wrote, this is not a bug. It is simply how the environment works. …

User's avatar

Continue reading this post for free, courtesy of The Pacific Divide.

Or purchase a paid subscription.
© 2026 Russ Wilcox · Privacy ∙ Terms ∙ Collection notice
Start your SubstackGet the app
Substack is the home for writing, podcasting, and media founders.