<p>What does it mean to build AI systems we can actually trust?</p><p><br></p><p>In this first part of our conversation with Saadia Gabriel (UCLA), we explore the deeply personal and technical journey behind her work on AI safety, misuse, and responsible NLP.</p><p><br></p><p>From experiencing targeted hate speech firsthand to receiving a best paper nomination, Saadia shares how her lived experience shaped her research — and why language models must be designed with both capability and risk in mind.</p><p><br></p><p>🧠 In this episode, we cover:</p><ul><li>How personal experiences influence AI research directions</li><li>The intersection of NLP, security, and privacy</li><li>Why LLMs can be both powerful and dangerous</li><li>What it means to build trustworthy AI systems</li><li>Lessons from working across multiple research paradigms</li><li>How to pursue high-impact research as a PhD or early-career scientist</li></ul><p><br></p><p>Resources &amp; Links:</p><ul><li><a href="https://arxiv.org/abs/2504.13203" target="_blank" rel="noopener noreferer">X-Teaming: Multi-Turn Jailbreaks and Defenses with Adaptive Multi-Agents</a></li></ul><p><br></p><p>Connect with Dr. Saadia Gabriel:</p><ul><li><a href="https://x.com/GabrielSaadia" target="_blank" rel="noopener noreferer">https://x.com/GabrielSaadia</a></li><li><a href="https://bsky.app/profile/skgabrie.bsky.social" target="_blank" rel="noopener noreferer">https://bsky.app/profile/skgabrie.bsky.social</a></li></ul>