📢 Our paper "AI safety for everyone" is out at Nature Machine Intelligence Nature Machine Intelligence . We challenge the narrative that AI safety is primarily about minimizing existential risks from AI. Why does this matter? A 🧵

Excited to announce our #NAACL2025 Oral paper! 🎉✨ We carried out the largest systematic study so far to map the links between upstream choices, intrinsic bias, and downstream zero-shot performance across 131 CLIP Vision-language encoders, 26 datasets, and 55 architectures!

🔗 Paper: aclanthology.org/2025.naacl-lon… Work done with amazing collaborators Isaac Slaughter, Kyra Wilson, Aylin Kamelia Caliskan, and Mona Diab! Catch our Oral presentation at Ballroom B, Thursday, May 1st, 14:00-15:30 pm!📷✨

At #NAACL2025 presenting the poster for our work! 📍 Hall 3, Session B on 🗓️ Wednesday, April 30 (tomorrow!) 🕚 11:00–12:30 Stop by to discuss the subjective standards of data selection in instruction following!

📢 New paper with Iason Gabriel is out! 2025 is being called the year of AI agents, with overwhelming headlines about them every day. But we lack a shared vocabulary to distinguish their fundamental properties. Our paper aims to bridge this gap. A 🧵

📣Thrilled to announce I’ll join Carnegie Mellon University (CMU Engineering & Public Policy & Language Technologies Institute | @CarnegieMellon) as an Assistant Professor starting Fall 2026! Until then, I’ll be a Research Scientist at AI at Meta FAIR in SF, working with Kamalika Chaudhuri’s amazing team on privacy, security, and reasoning in LLMs!

Super excited that I'll be joining the University of Washington Tech Policy Lab and UW NLP as a postdoc in the Fall working with Aylin Kamelia Caliskan to continue my research directions in situated evaluation, multimodal/lingual GenAI, and start exploring new directions in safety and alignment! Open to collabs😉

This dataset papers offers a rare glimpse into how LLMs are actually used in the wild. Over 94k real-world use cases, mapped by occupation and application type. A nice addition to the Anthropic paper I tweeted a while ago to study AI's societal impact. arxiv.org/abs/2503.18792

Thrilled to launch Prompt Adaptation, a state-of-the-art agentic system to automate prompt engineering 🚀

Today we're releasing Community Alignment - the largest open-source dataset of human preferences for LLMs, containing ~200k comparisons from >3000 annotators in 5 countries / languages! There was a lot of research that went into this... 🧵