20250918 - OpenAI fights the evil scheming AI! Which doesn't exist yet

if all else fails, tell the bot to act evil Text version: https://pivot-to-ai.com/2025/09/18/openai-fights-the-evil-scheming-ai-which-doesnt-exist-yet/ Patreon: https://www.patreon.com/davidgerard YouTube memberships: https://www.youtube.com/@PivotToAI hit "Join" Ko-Fi: https://ko-fi.com/A1529D5 Buy me nice things: https://www.amazon.co.uk/hz/wishlist/ls/3Q8VZW46J6DM6 Get an extremely cool Pivot to AI shirt or mug: https://pivot-to-ai.redbubble.com Sources: Detecting and reducing scheming in AI models https://openai.com/index/detecting-and-reducing-scheming-in-ai-models/ Stress Testing Deliberative Alignment for Anti-Scheming Training (PDF) https://static1.squarespace.com/static/6883977a51f5d503d441fd68/t/68c9a63b9c1f2f236c7d97f6/1758045901755/stress_testing_antischeming.pdf Previously on Pivot to AI: Anthropic, Apollo astounded to find a chatbot will lie to you if you tell it to lie to you https://pivot-to-ai.com/2024/12/19/anthropic-and-apollo-astounded-to-find-that-a-chatbot-will-lie-to-you-if-you-tell-it-to-lie-to-you/ 'Reasoning' AI is LYING to you! — or maybe it's just hallucinating again https://pivot-to-ai.com/2025/04/18/reasoning-ai-is-lying-to-you-or-maybe-its-just-hallucinating-again/ video: https://www.youtube.com/watch?v=dNT0LcCqtss&list=UU9rJrMVgcXTfa8xuMnbhAEA OpenAI announces GPT-5! Please Microsoft, don't kill us https://pivot-to-ai.com/2025/08/08/openai-announces-gpt-5-please-microsoft-dont-kill-us/ video: https://www.youtube.com/watch?v=0vxbHOTV7IA&list=UU9rJrMVgcXTfa8xuMnbhAEA AI doomsday and AI heaven: live forever in AI God https://pivot-to-ai.com/2025/08/17/ai-doomsday-and-ai-heaven-live-forever-in-ai-god/ video: https://www.youtube.com/watch?v=tAJIew3FAJ8&list=UU9rJrMVgcXTfa8xuMnbhAEA Full Pivot to AI playlist: https://www.youtube.com/playlist?list=UU9rJrMVgcXTfa8xuMnbhAEA