I was invited by the Department of Information & Public Relations, Belagavi to deliver a workshop on Media and AI to print and new media journalists.
My objective was to demonstrate a few different ways of how I use various AI chatbots and point out some of the issues one needs to be careful about.
Figure 1: Swapneel Patnekar presenting a workshop on Media and AI
Figure 2 – Agenda of the workshop
OpSec best practices
The first thing that I spoke was about being cognizant of the fact on the information that is shared with the AI chatbot. From an operational security (OpSec) perspective, this is extremely important.
I’ve seen people putting in PII and other sensitive information into the AI chatbot without knowing the implications of it.
Media and AI – Biases, logical fallacies and misinformation
Then, I introduced the journalists to Spinscore. Using AI chatbots, the creation and modification of content is extremely easy, thus, it’s important to separate the facts and the misinformation.
Welcome to SpinScore – an advanced AI tool designed to analyze and score potential biases, logical fallacies, and misleading information in content. Our system uses a combination of state-of-the-art Large Language Models and sophisticated mathematical algorithms to deliver comprehensive insights into the content you explore.
I’ve personally used Spinscore in the past few months and I have found it quite useful to uncover potential biases and incorrect information. I also tend to use it lately with my own writing to find my blind spots, so that I can improve my writing.
I encourage anyone, not just journalists to use this tool to optimize their reading/writing of news on the Internet.
A large focal point of my presentation was spent on using various chatbots for translating text from a link or a video from English to Kannada or Marathi language. If you have used an AI chatbot for translation of text, you will know, it’s not a hundred percent perfect.
I also spent sometime in prompt engineering, explaining the methodology and demonstrating a few use cases to generate content based on topics such as industrial waste, climate change etc.
Self-hosted AI chatbot
And lastly, I showed what a self-hosted LLM using Ollama and OpenWebUI looks like.
Figure 3: Self-hosted AI Chatbot
The benefits of self-hosting and running a local AI chatbot are many.
The workshop gave an exploratory tour of using AI chatbots for translation of text, video and generation of text based using prompt engineering.
My gratitude to the Department of Information & Public Relations, Belagavi for having me.
Recommended reading
If you enjoyed reading this blog post, you might find Why I’m rejoining social media interesting.