Filtir icon


No ratings
False claims eliminator with evidence provision.
Generated by ChatGPT

Filtir is an AI tool that helps fix "hallucinations" in text generated by ChatGPT, a powerful tool for writers that sometimes produces false claims. Filtir edits the text to remove these hallucinations and provides evidence to justify the edits.

The tool relies on a state-of-the-art biologicallarge language model, which may result in slower performance, especially when the model is not active.

Filtir determines whether a factual claim is true or hallucinated by relying on publicly accessible evidence available on the open internet. If appropriate evidence cannot be found, the claim is considered hallucinated and removed from the edited output.

Despite providing links to the evidence used to support its claims, Filtir can still make mistakes, and users are advised to check the evidence themselves where application context demands it.

The tool takes user privacy seriously and does not sell or share data with third parties for marketing purposes. Filtir's team includes Samuel Albanie, Vlad Bogolin, Anthony Buonomo, and Ioana Croitoru.

The tool's website also includes an About section, Frequently Asked Questions, and links to its Privacy Policy, API Data Policy, and Terms of Use.


Community ratings

No ratings yet.

How would you rate Filtir?

Help other people by letting them know if this AI was useful.


Feature requests

Are you looking for a specific feature that's not present in Filtir?
Filtir was manually vetted by our editorial team and was first featured on May 21st 2023.
Promote this AI Claim this AI

Pros and Cons


Fixes ChatGPT hallucinations
False claims eliminator
Edits and justifies text
Uses large language model
Utilizes open internet evidence
Removes hallucinated claims
Provides supporting evidence links
User privacy prioritized
No data selling
No third-party data sharing
Experienced team
Transparent about possible mistakes
Dedicated FAQ section
Inclusive documentation (privacy/Terms/API)


Performance may be slow
Possibility of mistakes
User has to verify evidence
Depends on publicly accessible evidence
Inability to identify appropriate evidence
No information about multi-language support
No information about integration capability


What is Filtir?
What does Filtir do?
What is ChatGPT?
What are 'hallucinations' in the context of ChatGPT?
How does Filtir determine if a fact is true or hallucinated?
How does Filtir fix hallucinations?
How does Filtir provide evidence?
What should I do if Filtir makes a mistake?
What does Filtir do with my data?
Who are the team members behind Filtir?
How can I contact Filtir's support?
Why does Filtir's performance slow down sometimes?
Can I use Filtir for professional writing?
Where can I find Filtir's Privacy Policy?
Where can I find Filtir's API Data Policy?
What are the Filtir's Terms of Use?
How does Filtir ensure user privacy?
Does Filtir share my data with third-party marketers?
What to do when the edited output still appears hallucinated?
Is there a limitation on the size of the text that Filtir can handle?


+ D bookmark this site for future reference
+ ↑/↓ go to top/bottom
+ ←/→ sort chronologically/alphabetically
↑↓←→ navigation
Enter open selected entry in new tab
⇧ + Enter open selected entry in new tab
⇧ + ↑/↓ expand/collapse list
/ focus search
Esc remove focus from search
A-Z go to letter (when A-Z sorting is enabled)
+ submit an entry
? toggle help menu
0 AIs selected
Clear selection