Have you ever wondered how Pangram works? Neural networks like Pangram are often black boxes: highly accurate, but mysterious and hard to explain.
Interpretability is the field of AI research concerned with studying how AI systems work. Over the past few months, we at Pangram have begun to apply interpretability methods to our production AI text detection models.
Pangram Space Visualization
From that work, today we’re launching Pangram Space, an interactive research project where you can explore the embedding space of Pangram 3.3.2 and watch how the model separates the classes of Human and AI text.
To see the project, visit Pangram Space!
Elyas Masrour is a founding engineer at Pangram. Since joining Pangram as it's second employee straight out of the University of Maryland, he has built out critical infrastructure such as the model serving API, role-based access controls, and supporting evidence pipelines. Elyas also works closely with the research team on projects like adversarial robustness, model interpretability, and heterogenous mixed content detection. Outside of work, Elyas enjoys a wide range of human creativity and expression, including filmmaking, reading, and exploring the city.
Related reading
Pangram is the only AI detector that outperforms human experts at identifying AI content
EditLens Accepted Into ICLR 2026
Marketers are Wasting Advertising Spend on AI-generated Content
Does Pangram detect Gemini 3?
The Latest in AI Detection Research
Checkfor.ai is now Pangram Labs
to our updates
