On this episode of How We Made That App, join host Madukar Kumar as he delves into the groundbreaking realm of AI in education with Dev Aditya, CEO and Co-Founder of the Otermans Institute. Discover the evolution from traditional teaching methods to the emergence of AI avatar educators, ushering in a new era of learning.
Dev explores how pandemic-induced innovation spurred the development of AI models, revolutionizing the educational landscape. These digital teachers aren't just transforming classrooms and corporate training. They're also reshaping refugee education in collaboration with organizations like UNICEF.
Dev’s deep dive into the creation and refinement of culturally aware and pedagogically effective AI. He shares insights into the meticulous process behind AI model development, from the MVP's inception with 13,000 lines of Q&A to developing a robust seven billion parameter model, enriched by proprietary data from thousands of learners.
We also discuss the broader implications of AI in data platforms and consumer businesses. Dev shares his journey from law to AI research, highlighting the importance of adaptability and logical thinking in this rapidly evolving field. Join us for an insightful conversation bridging the gap between inspiration and innovation in educational AI!
Key Quotes:
- “People like web only and app only, right? They like it. But in about July this year, we are launching alpha versions of our products as Edge AI. Now that's going to be a very narrowed down version of language models that we are working on right now, taking from these existing stacks. So that's going to be about 99 percent our stuff. And it's, going to be running on people's devices. It's going to help with people's privacy. Your data stays in your device. And even as a business, it actually helps a lot because I am hopefully, going to see a positive difference in our costs because a lot of that cloud costs now rests in your device.”
- “My way of dealing with AI is, is narrow intelligence, break a problem down into as many narrow points as possible, storyboard, storyboard color, as micro as possible. If you can break that down together, you can teach each agent and each model to do that phenomenally well. And then it's just an integration game. It will do better than a human being in, you know, as a full director of a movie. Also, if you know, if you, from the business logic standpoint, understand what does a director do, it is possible, theoretically. I don't think people go deep enough to understand what a teacher does, or what a doctor is just not a surgeon, right? How they are thinking, what is their mechanism? If you can break that down. You can easily make, like, probably there are 46, I'm just saying, 46 things that a doctor does, right? If you have 46 agents working together, each one knowing that,be amazing. That's a different game. I think agents are coming.”
Timestamps
- (00:00) - AI Avatar Teachers in Education
- (09:29) - AI Teaching Model Development Challenges
- (13:27) - Model Fine-Tuning for Knowledge Augmentation
- (25:22) - Evolution of Data Platforms and AI
- (32:15) - Technology Trends in Consumer Business
Links
Connect with Dev
Visit the Otermans Institute
Connect with Madhukar
Visit SingleStore
