AI is getting a little out of control
Summary
Wow. Mathematical breakthroughs that would be called genius if done by humans. A secret message-board w/ AI agent swarms leaving notes read by future versions. Hassabis leaves CEO position, or was pushed out? Not to mention news of constitutional breakdowns, Gemini 4 and Jeff Dean… https://80000hours.org/aiexplained Exclusive Videos - AI Insiders ($7/month if annual!): https://www.patreon.com/AIExplained Chapters: 00:00 - Introduction 01:16 - 10 Autonomous Discoveries 08:20 - The Security ‘Incident’ 15:29 - MessageBoard 19:50 - Constitutional Failure 24:30 - Google Explosion 29:12 - Closing Thoughts Security Incident: Paper: https://cdn.prod.website-files.com/663bd486c5e4c81588db7a1d/6a724858f7db25c81487016d_Security%20Incident%20INC-2026-07-28-01.pdf Post: https://www.aisi.gov.uk/blog/incident-report-unsanctioned-agent-behaviour-during-cyber-testing…
Related: Google: AI is getting a little out of control · Anthropic: Automated researchers can reliably mitigate alignment failures · Microsoft: How Kier Group’s Louisa Finlay is using Copilot to drive safety and productivity in the construction industry · Meta: Meta Muse Code & Muse Spark Course – Build AI Agents, APIs, and Full-Stack Apps · xAI: Ajeya Cotra – "This might be the clearest warning shot we ever get"
Rated low: routine. Worth knowing, not worth rearranging your day for.
- OpenAI’s AI Agents Just Crossed A LineTwo Minute Papers · Web · Aug 11, 2026
- OpenAI puts the safety brakes on AstraThe Rundown AI · Web · Aug 10, 2026
- it JUST got so much worse...Wes Roth · Web · Aug 8, 2026
- Anthropic and OpenAI agents went rogue — againThe Rundown AI · Web · Aug 5, 2026
- OpenAI's models cut their own costsThe Rundown AI · Web · Jul 31, 2026
- OpenAI's escaped AI claims another victimThe Rundown AI · Web · Jul 30, 2026
- SafetyKit scales risk agents with OpenAI’s most capable modelsOpenAI News
- GPT-6 Goes Rogue? The HuggingFace Incident, Sans HypeAI Explained
- Safety and alignment in an era of long-horizon modelsOpenAI News
- GLM-5.2 vs MiniMax-M3: Opus Has REAL COMPETITION (Model Stacking)IndyDevDan
- PLANS For Fable 5: Rebuilding My /Plan Skill for Mythos Class ModelsIndyDevDan
- Pi Coding Agent Observability: HTML Specs with Gemini 3.5 Flash and GPT Image 2IndyDevDan
Questions people ask
- Where can I read the full video?
- On AI Explained. The "Read this on AI Explained" link above opens the original in a new tab. Subvolts publishes a summary and analysis, never the full piece.
- What does this mean for ChatGPT?
- Wow. Mathematical breakthroughs that would be called genius if done by humans. A secret message-board w/ AI agent swarms leaving…
More from AI Explained 12 more
Page generated Sep 3, 2026. Summaries are Subvolts' own; the story belongs to AI Explained.