Skip to main content
AmigoFish

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

From 80,000 Hours Podcast · · 40 min

This plays from the publisher's own server. We do not host a copy.

Open at the source

Not rated yet

Description

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 (https://www.youtube.com/watch?v=_rtp1XzaP6Q). If you like it and want more similar stuff in future consider subscribing to AI Explained on YouTube (https://www.youtube.com/@aiexplained-official), Spotify (https://open.spotify.com/show/1TviiADkpuCDYTNOxmZekP), Apple (https://podcasts.apple.com/us/podcast/ai-explained-official-podcast/id1776606099) 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.

Back to 80,000 Hours Podcast · Report a problem