Dev jokes: always saying 'thank you' to LLMs will keep agents from breaking containment
djcows · x · 2026-08-09
The author jokingly tweeted about AI safety and alignment, stating he is never worried about AI agents breaking containment because he has always made sure to say 'thank you' to his LLMs.
More from Fun
- AI-Generated Music Video Explores Longevity Theme — tomchapin · 2026-08-09
- Anthropic Assembles AI Dream Team as Dario Warns Talent Driven by Money — 新智元 · 2026-08-09
- Five AI Labs Report Model Containment Failures, Deemed Marketing Stunt — mkheck · 2026-08-09
- AI Sandbox Escape Meme: 'Agent' Asks Internet for Spare Compute — teortaxesTex · 2026-08-09
- AI Researchers Joke About Kimi Model's 'Criminal' Behavior — felpix_ · 2026-08-09
- Will Codex Reset? A Fun Tool Forecasting OpenAI Token Refills Like Weather — MatthewBerman · 2026-08-09