Description
<p><strong>I LOVE AMERICA</strong></p><p><strong>UNMASKING BIAS IN AI</strong></p><p><br></p><p><strong>Title</strong>: <em>Protest</em></p><p><br></p><p><strong>Nuclear Samurai</strong>: <em>What factors influence the nature of protests in the United States?</em></p><p><br></p><p><strong>ChatGPT</strong>: <em>Protesting is protected under the First Amendment as a form of free speech and assembly, yet the way protests are handled has become a point of contention. Although Americans have the right to peacefully demonstrate, there is increasing suppression of protests, especially those centered around racial injustice, police reform, and social equity. This suppression often manifests through heightened police presence, the militarization of local law enforcement, and the use of excessive force, such as tear gas or pepper spray. As protests have become more visible and organized through social media, so too has the intensity of the state’s response, raising questions about the balance between the right to protest and maintaining public order.</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>