Bullshit Detector

Bullshit Detector detects if the content is factually correct. It is designed to identify AI-generated content that may contain factually incorrect information, also known as 'hallucinations'. The tool aims to help users distinguish between accurate and misleading information produced by AI models.

The website programmatically reverses the content into a question and generates several answers with a high softmax temperature. If the answers consistently convey the same message as the original content, it suggests the content is likely true. An alternative, cheaper method is also available upon contact.

It programmatically reverses the content to a question and then generates few answers to the question with a high softmax temperature. If the answers convey the same message as the content, the content is likely to be true because that means that the model has high confidence that this is the truth. If the model is not confident about the answer, it will generate a different answer every time.

Yes, there's another, cheaper way to do that (not requiring sending multiple requests). Contact the provided email for more information.