What is Filtir?
Filtir is a fact-checking tool designed to work with AI-assistants like ChatGPT. It is available as a ChatGPT Plugin and a web application. The primary function of Filtir is to evaluate text and determine if there is publicly available, auditable evidence to support the factual claims within that text.
When Filtir identifies a claim that lacks supporting evidence, it flags the claim, indicating that corroborating information could not be readily found. This helps users identify potential inaccuracies or "hallucinations" generated by AI, ensuring more reliable and factually sound content.
Features
- Fact-checking: Assesses whether there is public, auditable evidence to support claims.
- ChatGPT Plugin: Integrates directly with ChatGPT.
- Web App: Available as a standalone web application.
- Unsupported Claim Flagging: Identifies and flags claims that lack supporting evidence.
Use Cases
- Verifying information generated by AI language models.
- Fact-checking articles, essays, and other written content.
- Identifying unsupported claims in text.
- Ensuring the accuracy of AI-generated content.
FAQs
-
How do you determine whether a factual claim is true?
We do not arbitrate truth. Instead, we provide evidence in support of factual claims made by a piece of text. Where we are unable to identify appropriate evidence, we flag the claim as "unsupported". -
Which sources of evidence do you consider acceptable? How do you know if a source is "trustworthy"?
Our objective is to provide supportive evidence where we can find it. At present, we do not discard evidence based on reputation metrics - instead, we trust the user to make an assessment. -
Does filtir sell my data?
No. We do not sell your data or share your content with third parties for marketing purposes.
