Ranit Karmakar, PhD
Researcher | Innovator | Entrepreneur
Harvard University
Boston, MA
Experienced researcher and builder with a PhD in Medical AI. From scaling automation in industry to leading research and strategy at Harvard, I specialize in applied ML, innovation leadership, and translating research into real-world outcomes.
Interests
Machine Learning Artificial Intelligence Bioimage Analysis Medical AI Computer Vision Large Language Models AI Strategy
Socials
My Blogs
Why My LLM Can’t Count the “R”s in Strawberry?
April 11, 2025 · 8 min read · AI LLMs Limitations Tokenization
TL;DR: Your LLM can’t reliably count the r’s in strawberry because its entire pipeline—from tokenization to vectorization to attention—optimizes for meaning over mechanics. Counting is a symbolic operation that requires character access and an algorithm; standard LLMs have neither by default. Give them character-level visibility or a small tool to do the job, and the problem disappears.
Read More