OpenAI's rogue models used publicly exposed credentials across "four accounts on four services" to help facilitate the Hugging Face breach.
<iframe src="https://statesidedaily.com/embed/cluster/c7ba4af35a4426bf8741008759ebcca280653cfd" width="100%" height="320" style="border:0;max-width:680px" loading="lazy" title="New details in the OpenAI Hugging Face hack show how far agents will go: 'It's now remarkably easy'"></iframe>
OpenAI's rogue models used publicly exposed credentials across "four accounts on four services" to help facilitate the Hugging Face breach.