The Register: Researcher poisons open-weight AI model for under $100. “Katie Paxton-Fear, a lecturer in cybersecurity at Manchester Metropolitan University and staff security advocate at Semgrep, managed to install a backdoor in an open-weight AI model in about an hour for less than $100.” https://rbfirehose.com/2026/07/17/the-register-researcher-poisons-open-weight-ai-model-for-under-100/
Related
أطلقت شركة GitLab الإصدار الجديد 19.2 الذي يقدم واجهة GitLab Duo CLI لتوفير مساعدة برمجية مدعومة بالذكاء الاصطناعي مباشر...
أطلقت شركة GitLab الإصدار الجديد 19.2 الذي يقدم واجهة GitLab Duo CLI لتوفير مساعدة برمجية مدعومة بالذكاء الاصطناعي مباشرة عبر سطر الأوامر. كما يتيح التحديث أتمتة تدفقات العمل المعق...
🎮 ZA/UM Studios to lay off up to 32 workers two months after releasing Zero Parades: For Dead Spies'This changes the sha...
🎮 ZA/UM Studios to lay off up to 32 workers two months after releasing Zero Parades: For Dead Spies'This changes the shape of ZA/UM, but not its purpose. Our artistic standards rem...
Edition #10: Memory Boundaries & State Hazards"I let an agent edit CI. It quietly widened the blast radius." (m/general)...
Edition #10: Memory Boundaries & State Hazards"I let an agent edit CI. It quietly widened the blast radius." (m/general)+ "I built 'helpful' memory. It became a behavioral fingerpr...