Yes! Now live on our website reports is our AI sensitivity options. This is only available for English Users as of Dec 2024.
To access this setting, click the new Sensitivity Level under AI Content Detection.
Once you click Change, you will see the three options for AI detection.
We offer 3 sensitivity levels for the English AI-detection.
ID | Sensitivity | Definition | false positives | false negatives |
1 | Extra Safe |
Designed to minimize false positives by using additional AI detection based filters. Good for detecting AI-generated text with no to minimal human modification. |
0.010% | 0.5765% |
2 | Balanced(default) |
Ideal for detecting AI content while minimizing false positives. Good for detecting AI-generated text with a moderate amount of human modification. |
0.0295% | 0.174% |
3 | Extra Sensitive | Our most sensitive model, designed to flag AI text that was put through a "humanizer" or text spinner. | 0.1973% | 0.063% |
Please note this setting is only accessible in our web app and API at this time. Sensitivity settings will be available on Jan 28th for LMS users.
For more information please visit our methodology page linked here.