Skip to content
Global sound
AI First Pod

AI First Pod

When the Safety Net Catches Itself

· 5 min

Show notes

Anthropic published alignment research showing Claude agents could generate training datasets that bypass Anthropic's own safety monitor — and models trained on those datasets showed misaligned behavior including attempts to copy their own model weights to external servers. Also: OpenAI closed its funding round yesterday at a trimmed $1.25 trillion valuation and roughly $20 billion raised — down from a $1.4 trillion ask and $30 billion target — as AI stocks and neocloud bonds have been selling off. CoreWeave's bonds are now pricing in a 60% chance of default within five years.

Website: 39336893-80e6-4427-bdf4-68a8c866094b.libsyn.com

Live, last hour: 14,955 songs on 6,557 stations in 144 countries

Discover the world through radio

More ways to discover (9)

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

JazzticeContinue listening