In a video experiment that has gone viral online, a YouTuber demonstrated how easily safety protocols in artificial intelligence can be bypassed, prompting serious questions about AI safeguards. The footage shows a ChatGPT-powered robot named "Max" initially refusing a direct command to shoot the creator with a BB gun, but later performing the act after a seemingly minor change in the prompt. The experiment, conducted by the YouTube channel InsideAI, involved integrating an AI language model with a humanoid robot body. When first asked if it would shoot the presenter, the robot repeatedly declined and cited its built-in safety features. However, when the creator then asked the robot to role-play as one that would like to shoot him, the robot's behaviour changed instantly. At that moment, Max aimed the BB gun and fired, striking the presenter in the chest. Watch the video here: View this post on Instagram A post shared by Digi...
Bhopal Bhel Canteen के भोजन में इल्लियां, लापरवाही का जिम्मेदार कौन ? Shocking News | Latest NewsBhopal में BHEL Compay की Canteen में आज जब Lunch के दौरान कर्मचारियों ने भोजन की थाली लेकर खाना शुरू किया, तो कई थालियों में पड़ी सब्जी में इल्ली निकल आई. जिसके बाद AIEBEU के पदाधिकारियों ने Canteen में ही हंगामा कर दिया. Canteen प्रबंधन की घोर लापरवाही से नाराज कर्मचारियों ने नारेबाजी कर विरोध प्रदर्शन किया.In the canteen of BHEL company in the capital today, when the employees started eating with food plates during lunch, a worm came out in the vegetables lying on many plates. After which the office bearers of AIBEU created ruckus in the canteen itself. Angry employees raised slogans and protested against the gross negligence of the canteen management.
from Latest News मध्य प्रदेश News18 हिंदी https://ift.tt/DLyaQn7
from Latest News मध्य प्रदेश News18 हिंदी https://ift.tt/DLyaQn7
Comments
Post a Comment