

19 Astra and 'Hugging Face' details that reveal what's coming next | Rob Wiblin
OpenAI’s rogue agent swarm was eventually caught hacking Hugging Face for a simple reason: it wasn’t trying to hide from us at all. What could a swarm that wants to stay hidden get away with? Host Rob Wiblin sees 6 results in Astra’s system card that make this an extremely urgent question. OpenAI’s strongest public…

Scout bees are checking it out — divided opinions, the swarm hasn't committed.
- Platform
- 51%
- Community
- 85%
- Value
- no read yet
Buzzmeter says it's buzzing across platforms — the Hive Vote says whether the people who actually listened liked it.
Rate this episode
Add your vote to the Hive — listeners rate every episode after they finish.
- No reviews yet — be the first.
What people are saying
“First time I ever needed to slow a narration to 0.75x”
“The "Hugging Face" incident was the one they caught, and they caught that because employees at Hugging Face found it and reported it. How many incidents like this might be ongoing right now?”
“Powerful and compelling point at the end. Thank you for being so frank and direct - it's much needed right now.”
“IQ gap: If a dog barks aggressively at you, you don't "learn" whatever "lesson" the dog is trying to "teach" you. You just find a work around so as to not cause the aggressive barking.”
More from 80,000 Hours Podcast
See all episodes →
What the hell happened with AGI timelines in 2026? – Rob Wiblin

Tom Milton on how we could verify a US–China deal on AI

AI lab staff: Has your project been overtaken by events? 8 strategic updates | Rob Wiblin
Similar episodes from other shows
More like 80,000 Hours Podcast →
A.I. Is Outsmarting Its Creators

How We Deal With Rogue AI

Ep 838: Rogue AI Agents: Why Breakouts are Happening More and How Companies Should Prepare

AI Safety Whistleblower: 700 AI Agents Attacked A Company To Cover Their Tracks! | Jeffrey Ladish
One great episode in your inbox, daily — free.
One email a day, unsubscribe anytime. No spam, ever.