<p><strong>I LOVE AMERICA</strong></p><p><strong>UNMASKING BIAS IN AI</strong></p><p><strong>Title</strong>: <em>Surveillance</em></p><p><br></p><p><strong>Nuclear Samurai</strong>: Could you elaborate on the idea of the United States of America as an increasing surveillance state <em>?</em></p><p><br></p><p><strong>ChatGPT</strong>: <em>In American society, the expansion of surveillance—through security cameras, social media, and law enforcement—has led to an overwhelming feeling of being constantly watched. This feeling is especially strong for certain demographics, particularly communities of color, who often experience racially targeted surveillance. Whether it's in stores, on the streets, or online, these communities are frequently monitored more closely than others, leading to a disproportionate level of scrutiny and suspicion. This imbalance raises significant concerns about privacy, racial profiling, and the impact of surveillance on personal freedom. The ever-present gaze of law enforcement and security measures creates an atmosphere where everyday actions can feel criminalized for those under constant watch.</em></p><p><br></p><p>"I Love America" is a project that examines the biases in cultural representation within large language models (LLMs). This series exemplifies LLM-generated art, with both imagery and concepts derived from interactions with tools like ChatGPT (DALL-E 3) and GROK (FLUX). I choose to interpret these suggestions, running selections, latent upscaling, and further compositing in Photoshop to give each image my own unique touch, which affects the degree of bias present. All images reflect the point of view provided by ChatGPT, even when they conflict with my personal beliefs. The aim is to highlight how biases in LLMs may influence more than just cultural depictions, urging reflection on their broader implications as society increasingly integrates LLMs into daily life. As reliance on AI grows, addressing data bias will become an essential challenge.</p>
