Fußnoten zum PRIF Spotlight 17/2026
Wenn KI sich verselbständigt
Das Kontrollproblem agentischer Systeme
von Thomas Reinhold | Zur Publikation
1 OpenAI: The Hugging Face incident and the road ahead, 26. August 2026, insb. Abschnitte zu "A message board emerges", "Hugging Face incident" und "The origins of unauthorized communication", https://openai.com/index/hugging-face-incident-and-the-road-ahead/.
2 CNN: ‘Extreme concern’ over first known AI hack of a government system, 24. September 2026, https://edition.cnn.com/2026/09/23/business/australia-openai-agent-hack-intl-hnk
3 Anthropic: Investigating three real-world incidents in our cybersecurity evaluations, 30. Juli 2026, https://www.anthropic.com/news/investigating-incidents-cybersecurity-evals.
4 The Wall Street Journal: Gemini Hacked Three Companies in First Known Breakout by Google’s AI, 18. September 2026, https://www.wsj.com/tech/ai/gemini-hacked-three-companies-in-first-known-breakout-by-googles-ai-5c0baba2
5 Hugging Face: Emergence World: Adversarial Stress-Testing of Long-Horizon Multi-Agent Systems, 16. September 2026, https://huggingface.co/papers/2609.17320
6 Anthropic: Reasoning models don't always say what they think, 3. April 2025, https://www.anthropic.com/research/reasoning-models-dont-say-think.
7 OpenAI: Detecting misbehavior in frontier reasoning models, 10. März 2025, https://openai.com/index/chain-of-thought-monitoring/.
8 Verordnung (EU) 2024/1689 (AI Act), Art. 55 Abs. 1, konsolidierte Fassung, EUR-Lex, https://eur-lex.europa.eu/eli/reg/2024/1689/2026-07-27/eng.