AI detection just got a lot better: Announcing Checkfor.ai
Introducing Checkfor.ai: paste any text and detect AI-generated content with high accuracy — the launch of what would become Pangram.
Screenshot of the original Checkfor.ai website.
NOTE: We've changed our name to Pangram Labs! See our blog post for more details.
Today, we are launching Checkfor.ai, a tool to detect AI-generated content with a simple copy and paste.
Our mission is to protect the digital world from low-quality AI-generated content that threatens authentic human voices. Our product allows content publishers, review platforms, educators, and creators to verify that their content was written by a real human being.
Why do we believe we can solve this challenging problem? We are a small team of experienced machine learning researchers and engineers who simply know how to bring working models into production environments. Our team has shipped real-world machine learning products at Google, Tesla Autopilot, and Nuro. We are obsessed with reliability and trust, and will not just stop when our test set accuracy hits 99%. Our goal is not just to be the best-in-class detector, but to be reliable enough for high stakes, real-world deployments that demand low false positive and false negative rates.
We’ve only been working on this problem for about a month, but have already made great progress. While our detector isn’t perfect, we believe it is already better than competitor detectors by a good margin, especially on creative writing and user-published online content. We’re looking forward to improving the performance of the tool and sharing some exciting results in the coming weeks.
Give it a shot at Checkfor.ai!
Max is a seasoned machine learning engineer. He most recently worked on autonomous vehicles at Nuro, leading their active learning effort. He has a long history of deploying successful machine learning products at Google, Two Sigma, and Yelp.
Max holds a B.S. in theoretical computer science and an M.S. in artificial intelligence from Stanford University. In addition to his passion for building, he is also an active member of the Magic: the Gathering cube community.
Bradley is an AI researcher and expert in building deep learning products in industry. He recently led the deep learning research group at Absci, a generative AI drug discovery company, and previously was a member of the core computer vision team at Tesla Autopilot.
Related reading
Can Pangram Detect Claude Opus 5?
Statement on Biden's AI Safety Executive Order
Can Pangram Detect Claude Sonnet 5?
The Information Theory Behind Why AI Writing Sucks
Why does Pangram have a minimum word count?
