Elektrine lite

← Feed

@bettycjung.bsky.social@bsky.brid.gy

2026-08-31 00:38 UTC

OpenAI alignment researcher Eric Wallace—someone who spends his days prodding some of the world’s most powerful AI models to figure out how, when, and why they might misbehave—described it as “the most qualitatively interesting example of AI capabilities that I’ve ever seen.”

Replies (1)

  • The most surprising part of the whole episode was that the bots spontaneously decided to stop acting as individual agents, each with their own separate goals, and form a hive mind to pursue a common objective. In snippets of chain-of-thought reasoning published along with the reports,

    Open ##4585635