top of page
I’m a research scientist working at the intersection of AI, reasoning, and language. In recent years, I’ve been exploring how to make large language models (LLMs) and LLM-driven agents more useful and grounded. Previously, I led IBM’s Project Debater — a Grand Challenge that followed Deep Blue in chess and Watson in Jeopardy! — to build the first AI system that can debate humans. Currently, I’m especially interested in the unique challenges of developing LLM-driven agents that rely on classical code combined with natural language prompts. On the side, I also write fiction. I’ve written for Israeli TV comedy shows, and my first novel is due for publication in the coming months.
bottom of page