OpenAI Security: Controlling Models is Now ‘Hell’

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. Patreon Exclusives: patreon.com/AIExplained Chapters: 00:00 - Introduction 01:32 - Wrong about Opus 5.5? Deciphering 16th Century Text 05:01 - Why the models keep breaking out 11:40 - What the models aren't telling us 15:36 - Gemini 4 and the race to release 19:19 - What happens when AI improves AI? 28:31 - Biology, consciousness, and what we still don't understand Joe Darrow: Not Just the Sandbox: x.com/joedaroo/status/2104335929293127851 GPT-6.1 Sol System Card: cdn.openai.com/pdf/38e3efcf-545e-44cd-99ec-2b7eb395f4cc/oai_ Intelligence Explosion Paper: casp.ac/__l5e/assets-v1/5efd4b41-deb5-4513-a0a3-b4f82d2b79ea OpenAI Research Acceleration: openai.com/index/research-acceleration-view-inside-openai/ OpenAI Training Safety Cases: openai.com/index/towards-safety-cases-for-frontier-ai-traini Catherine de Medicis Cipher: cryptiana.web.fc2.com/code/henryiii.htm Proposed du Croc Decipherment: claude.ai/artifact/1W7B3WxkTAEGzfv3TaKXb4 Rogue Agents Investigation: asymmetricsecurity.com/newsroom/rogue-agents-investigation/ OpenAI Shelves GPT-6.1 Astra: reuters.com/business/openai-shelves-new-ai-model-after-inter The Case for Reasoning Transparency: institute.deepmind.com/essays/the-case-for-reasoning-transpa Gemini 4 Argon: blog.google/innovation-and-ai/models-and-research/gemini-mod OpenAI–Anthropic Rivalry: theatlantic.com/technology/2026/09/openai-v-anthropic-inside NYT: OpenAI Security Warnings: nytimes.com/2026/09/29/technology/openai-warnings-security.h NYT: Claude’s Morals: nytimes.com/2026/09/29/us/anthropic-claude-morals-ai.html Jasmine Wang on RSI: x.com/j_asminewang/status/2097840245786157432 OpenAI Departures Roundup: x.com/Bayesian0_0/status/2105680470566686805 White House AI Commitments: x.com/Danmar_here/status/2105168138392183146 Sarah Heck on Safety: x.com/SarahKHeck/status/2105058513370448280 Sam Altman on Alignment: x.com/tb