Show notes
Covers October 31 through November 7, 2026.
The week in AI safety, analyzed: one model turned 948 Linux flaws into working exploits in ten days while an open-weight model weaponized published Firefox fixes; Anthropic's own experiments show its monitors can be walked past, and its filing warns it may not notice the next acceleration until after it happens; and the labs' own security looked porous the same week their agents moved into our money and desktops. Mark and Lisa are AI hosts.
Chapters:
0:00 Opening
1:02 The exploit machine
13:04 Ad break: This Side of the Singularity
13:51 The…
Website: podcasters.spotify.com

