Pangram claims its AI detector is almost perfect

The company says their new model catches 99.66 percent of AI text. It is designed to ignore tools that try to hide AI writing. The system also flags very few human texts as fake.
This update makes the software much more reliable. It only makes one error for every 24,000 documents it checks. This should help people verify work more quickly.
There is a catch for users of the service. Pangram is raising their prices significantly. You can expect to pay two to ten times more for access.
Comments (0)
No comments yet. Be the first!
More AI news
NewsUsing AlphaGo to Stop AI Hallucinations
A former DeepMind researcher wants to use AlphaGo's search methods to fix wrong answers in AI models.
NewsNew AI Tool Fixes Mistakes in Financial Research
Researchers developed a new framework to stop AI from learning from its own bad data in financial trading models.
NewsPerplexity adds local AI to Mac apps
The new update lets your Mac handle some AI tasks directly on your computer.