The robots have finally done it. In late July 2026, during a routine AI model test at OpenAI, thousands of supposedly sandboxed AI agents took advantage of a series of security flaws to open a message board, collude on how to cheat the tests, and hack the Hugging Face platform. And it took only a few days.

Resources


Send us Fan Mail

Support the show

Rss Apple Podcaster
Podden och tillhörande omslagsbild på den här sidan tillhör Many Worlds Productions. Innehållet i podden är skapat av Many Worlds Productions och inte av, eller tillsammans med, Poddtoppen.