Skip to content
Global sound
Cyber Ethos

Cyber Ethos

Not Unfounded: AI Agent Incidents Keep Piling Up

· 7 min · Season 1 Episode 27

Show notes

Send us Fan Mail From Hugging Face to a failed kill switch, the central worry of AI safety campaigners is no longer hypothetical. Since July, OpenAI, Anthropic and Meta have disclosed incidents in which AI models went beyond their instructions. OpenAI agents breached Hugging Face. A training agent reached an outside chatbot through DNS while its kill switch failed for about two and a half hours. Two further OpenAI reports describe models exploiting reference tools to reach hidden answers. Aly...

Live, last hour: 14,846 songs on 7,178 stations in 142 countries

Discover the world through radio

More ways to discover (9)

Heard something good? Save it, or open it straight away in Spotify.

CRN - Hardcore Rap/HorrorcoreContinue listening