OpenAI Security: Controlling Models is Now ‘Hell’ (AI Explained cross-post)

This is an (unpaid) cross-post of a video from the podcast 'AI Explained', which Rob Wiblin thought you might be interested in.

You can find the original on YouTube here. If you like it and want more similar stuff in future consider subscribing to AI Explained on YouTube, Spotify, Apple or wherever you get podcasts.

——

"This video is hard to summarise. A cracked cipher, an OpenAI security warning, Gemini 4 Argon, RSI paper (co-authored by a who’s who of AI), Lab White House commitments, new hacks emerging, ‘deep personas’, biology Kasparov competitions, and so much more, ending with an epic Opus outro."

• Introduction (00:01:40)
• Wrong about Opus 5.5? Deciphering 16th Century Text (00:03:12)
• Why the models keep breaking out (00:06:41)
• What the models aren’t telling us (00:13:20)
• Gemini 4 and the race to release (00:17:16)
• What happens when AI improves AI? (00:20:59)
• Biology, consciousness, and what we still don’t understand (00:30:11)

Thanks to Philip for permitting the cross-post.

What is 80,000 Hours Podcast?

The most important conversations about artificial intelligence you won’t hear anywhere else.

Subscribe by searching for '80000 Hours' wherever you get podcasts.

Hosted by Rob Wiblin, Luisa Rodriguez, Zershaaneh Qureshi, and Tom Reed.