About 1 month ago, I published this post below:

Letter in the Ocean: Why should we keep writing? COMPLETELY AI vs HUMAN generated posts: 🤖 vs 🧑
Ömer Berat Sezer ・ Feb 13
In that post, I mentioned the increasing number of posts generated by COMPLETELY AI on the internet and DEV.to. We've even talked/discussed with many authors in the comments section, we had a brainstorm. I've seen that many people were actually complaining about this issue.
As I was thinking about this issue, I realised that it is actually possible to separate content that is COMPLETELY AI generated with a method using both AI app and humans.
I've seen many AI content detector software on the internet, but frankly I don't like any of them because they don't properly describe the AI detected patterns. They produce low quality results.
Open Source AI-Content-Detector App
To show how simple it is and how effective Prompt Template is, I developed an Open Source AI Content Detector App using AWS Bedrock and Llama 3.1 405B parameters LLM.
GitHub Link: https://github.com/omerbsezer/AI-Content-Detector
git clone https://github.com/omerbsezer/AI-Content-Detector
pip install -r requirements.txt
python -m streamlit run .\main.py
It is simple tool using AWS Bedrock Service - Llama 3.1 405B
- to give AI generated score,
- to analyze and explain how much input text is AI generated.
I tested with COMPLETELY AI Generated and HUMAN Generated Content
AI Score for Human Generated Text in App
Please have a look below Demo GIF/Video for Human-Generated Post:
AI Score for COMPLETELY AI Generated Text
Please have a look below Demo GIF/Video for AI-Generated Post:
How do we proceed to separate COMPLETELY AI vs HUMAN generated posts?
As mentioned above, in Dev.to, we can use both community and AI app together to eliminate the COMPLETELY AI posts.
Step 1: Give people the option to tag COMPLETELY AI-generated content, and if 5-6 people agree, move to step 2.
Step 2: Uploading the content to the AI Content Detector app and if it scores above 50%, notifying the author with detected patterns, removing the article or ensuring that more people do not see the article.
Maybe, Dev.to management will see this article, and maybe it will inspire them.
Let's Discuss! 🤝
How is this idea? Alternative Ideas?
I am throwing a letter in a bottle into the ocean, maybe someone reads it, maybe nobody.. If anybody read/agree, pls write something in comments, or am I alone?