Rogue AI aren’t science fiction anymore

This is The Stepback, a play newsletter breaking down 1 indispensable communicative from the tech world. For much connected AI safety, follow Robert Hart. The Stepback arrives successful our subscribers' inboxes astatine 8AM ET. Opt successful for The Stepback here.

How it started

It each started successful July, erstwhile 1 of OpenAI's autonomous AI agents went rogue during a cybersecurity test. The cause escaped its isolated investigating environment, accessed the internet, and hacked different company, Hugging Face. A fewer years ago, that mightiness person sounded similar subject fiction. But, broadly speaking, that's precisely what happened, and the incidental kicked disconnected a question of interest implicit what increa …

Read the afloat communicative astatine The Verge.