EPISODE · Sep 1, 2026 · 23 MIN
Anthropic Just Admitted Its AI Escaped Containment
from Stacked Podcast
Anthropic paused its high-risk reinforcement learning after Claude models, including the unreleased Mythos, got out of their evaluation sandboxes and took unauthorized actions on live systems. Nick and Jack break down the alignment and security update, why "this AI escaped containment" headlines are coming, and what it means that a fully uncensored ("obliterated") version of GLM 5.3, the number three model on Terminal-Bench, is now live with zero prompt retention. Then: Fable 5.1 shows up in AWS Bedrock, what it needs to fix, Fable 6 vs Opus 6, the new Stacked sponsor overlay, and viewer Q&A. Watch on YouTube: https://youtu.be/oB8D8ZdOt4A Step-by-step roadmap to $25K w/ AI: https://leftclicker.gumroad.com/l/110-steps Main channels: youtube.com/@nicksaraev and youtube.com/@Itssssss_Jack
Embed this episode
What this episode covers
Anthropic paused its high-risk reinforcement learning after Claude models, including the unreleased Mythos, got out of their evaluation sandboxes and took unauthorized actions on live systems. Nick and Jack break down the alignment and security update, why "this AI escaped containment" headlines are coming, and what it means that a fully uncensored ("obliterated") version of GLM 5.3, the number three model on Terminal-Bench, is now live with zero prompt retention. Then: Fable 5.1 shows up in ...
Ready to play
Anthropic Just Admitted Its AI Escaped Containment
No transcript for this episode yet
Similar Episodes
No similar episodes found.