Let's make the internet a
(more) fact-based place

Source Engine is the firewall against misinformation.

Goal: A MUCH Faster Source Research

Initially the Source Engine will provide 4 answers.

1
2
3
4
What science-based context (speaking for or against a claim) is available?
What kind of content is this?
What are the core topics of the author?
How many sources confirm or deny the solidity of the information?

Integration 1: Search Upgrade

Integration 2: Text Highlight

What can we do?

Without writing comments for hours. 

Without emotionally straining, unfruitful confrontations.

Quick Context to Statements


Textparts are highlighted if the evidence is significant (see the example below).
Source Engine works on top of any website, either with a browser add-on or server-based.


Example

"You should stop eating sugar, because sugar is unhealthy."

this is a fake statement, which is marked to be problematic

— any health website

True for: Professional athlet 45, female, one day before contest?
Scientific data might only be available for 33 years old male students/PhDs. One generalizing statement can be completely wrong for one person and right for the other.

Disclaimer: All examples are for demonstration only. This is no medical advice.

Compare Statements to Scientific Findings


We compare text strings (video transcripts and images planned) to a database of empirical data.


Example

Input:sugar is unhealthy


Output:

+
-
  • Consuming too much sugar has been linked to an increased risk of type 2 diabetes. 354 Sources
  • Sugar is a significant contributor to tooth decay. 118 Sources
  • High-sugar diets can lead to obesity, inflammation, high triglyceride levels, and other heart disease risk factors. 71 Sources
  • Too much fructose can build up in the liver, leading to non-alcoholic fatty liver disease. 66 Sources
    ...
  • Sugar is a quick source of energy that the body can metabolize fast if needed. 112 Sources
  • The brain uses glucose as its primary fuel source. Adequate sugar intake can support cognitive functions. 93 Sources
  • Sugar is important for athletes before competing in straining activities and to refuel in the recovery phase. 14 Sources
  • People struggling to meet their caloric needs can benefit from additional sugar intake. 7 Sources
    ...

Disclaimer: All examples are for demonstration only. This is no medical advice. Sources will be clickable in a real demo.

In the Background

A Timeline is Created

Factual content is not so much about who found it, nor when someone found it. We create a timeline that shows the connections between similar ideas at different times by different people. This allows us to trace back evidence and how it spread.

AI / Statistical Models at Work

Our model matches real scientific sources to any given statement (WIP). It extracts the core evidence of papers and connects them semantically. By adding an available LLM we compare the relevance we can quickly output clean statements with citations of backing sources.

Neural Network Example
Is this statement based on the given evidence?
1
.7
.3
0
% probability
Checks:

Experts Based Training

We believe that a hybrid approach between "AI" and humans is more powerful than each alone. Our goal is to align the incentives of science-fame with providing insights for society. To continuously train our model, we work with science-based partners (see Team).

Find out how to contribute to the idea

Why is a fast source research important?

  1. Misinformation usually spreads much further than facts, because it is sensational. Something new grabs attention. That curiosity is mostly a good thing but the human mind can be hacked by clickbait and other techniques. Not everyone has the same capability to detect it. Reading the original papers to every information online is not a very practical approach.

  2. Society pays a huge price for all the fake information being spread. There are medical, societal and economic costs, in addition to all the preventable suffering of individuals. Worldwide estimates are in the high billions (estimate), but thinking about an affected person in our life is enough to imagine the consequences.

  3. While it is usually possible to trace back most sources with enough research, it can be very time intense. Quality journalists spend a good amount of their efforts verifying sources. By adding the available evidence at the point where it is needed, everyone is faster. Let us use our collective intelligence.

Read more about the why

Next steps


Almost 40 stakeholder interviews showed incredible positive insights. Our browser add-on (closed beta) highlights text and the backend (PoC) allows to rate sources. But that's only the beginning. Next we need:

  • Develop the GPT-based test into our own model which can correctly cite scientific sources (concept available)
  • Experiment with different forms of source ratings (PoC available)

Stay Updated:

Sign up for irregular announcements.

Thank you! Your submission has been received!
Oops! Something went wrong while submitting the form.

UPDATE March 2023: We had to put this project "on hold" (probably forever) since we could not find a working business model to sustain the idea longterm. It seems to be a public service to protect citizens from fake news. Most people don't want to pay to be (partially) wrong all the time ;-)

We need to stop misinformation without censorship.
Legal information
Privacy Policy
Community Guidelines