Shaun Wei, CEO of RealChar, discusses the evolution of Rivia, an AI assistant for handling phone calls. Topics include leveraging Generative AI, technical challenges in AI model deployment, and the complexities of self-driving cars. The podcast explores the use of AI to streamline customer service interactions and prioritize more important tasks in daily life.
Read more
AI Summary
AI Chapters
Episode notes
auto_awesome
Podcast summary created with Snipd AI
Quick takeaways
Rivia integrates Generative AI and ML to automate phone calls, enhancing consumer interactions.
AI deployment challenges underscore the necessity of realistic training environments and iterative capabilities improvement.
Deep dives
Revolutionizing Customer Service with AI
Utilizing a unique blend of Generative AI and traditional ML, Sean introduces Rivia, a groundbreaking consumer application. By combining these technologies, Rivia aims to revolutionize the consumer experience by automating interactions that traditionally require human input. Through concepts like "Design OS," Sean envisions leveraging parallel operation in robotics to scale AI-driven services, offering potential solutions to common customer service challenges.
Navigating the Complexity of AI Deployment
Based on Sean's journey from Google Assistant to self-driving cars, he highlights the challenges of deploying AI at scale. Drawing parallels with self-driving car simulations, he stresses the importance of creating safe yet realistic virtual environments for AI training. Sean's technical insights underline the need for fast and reliable AI systems, emphasizing the iterative process of enhancing AI capabilities through real-world interactions and data.
Enhancing AI Reliability and Scalability
Discussing the critical aspects of AI reliability, Sean delves into designing robust systems that can adapt to changing demands. Emphasizing the significance of scalability and real-time observability, he explains the need for adaptive models and fallback mechanisms to ensure consistent performance. By sharing his experiences in managing event-driven architectures and intelligent task distribution, Sean offers practical insights into optimizing AI solutions.
Maximizing Intelligence Utilization
Emphasizing the transformative potential of AI, Sean envisions a future where leveraging enhanced intelligence equates to productivity. He highlights the shift towards utilizing AI capabilities as a measure of wealth and efficiency, emphasizing the importance of adapting to evolving AI technologies. Through thoughtful deployment strategies and continuous learning, Sean advocates for open-minded exploration of AI tools and methodologies to unlock innovative solutions and drive meaningful progress.
Sean Wei, the CEO and co-founder of RealChar, shares his journey from working in the autonomous vehicle industry to creating an open-source voice assistant project called Realchar, which eventually evolved into Rivia, a voice AI assistant focused on managing personal phone calls.
The Future of AI and Consumer Empowerment // MLOps podcast #244 with Shaun Wei, CEO & Co-Founder of RealChar.
A big thank you to LatticeFlow for sponsoring this episode! LatticeFlow - https://latticeflow.ai/
// Abstract
Explore the groundbreaking work RealChar is doing with its consumer application, Rivia. This discussion focuses on how Rivia leverages Generative AI and Traditional Machine Learning to handle mundane phone calls and customer service interactions, aiming to free up human time for more meaningful tasks. The product, currently in beta, embodies a forward-thinking approach to AI, where the technology offloads day-to-day burdens like scheduling appointments and making calls.
// Bio
Shaun Wei is a well-connected technology professional with a rich background in developing and analyzing artificial intelligence systems. In 2018, Shaun played a pivotal role in the advent and deployment of Google Duplex, a remarkable AI capable of handling natural conversations and performing tasks such as booking hair salon appointments and restaurant reservations via telephone. His involvement wasn't just limited to the developmental side; Shaun also uniquely positioned himself on the receiving end, gathering insights by interviewing users directly impacted by the technology. This dual perspective has enabled Shaun to grasp both the technical underpinnings and the human-centric applications of AI, making him a valuable asset in the tech industry.
// MLOps Jobs board
https://mlops.pallet.xyz/jobs
// MLOps Swag/Merch
https://mlops-community.myshopify.com/
// Related Links
https://www.rivia.tech/
Timestamps:
[00:00] Shaun's preferred coffee
[00:28] Takeaways
[03:30] Please like, share, leave a review, and subscribe to our MLOps channels!
[03:57] AI in Production: Challenges & Insights
[06:13] AI Scheduling and Assistance
[08:00] Technical Challenges in AI
[12:36 - 14:06] LatticeFlow Ad
[14:09] Handling Challenges in AI
[15:52] Learning driving and technical aspects
[19:04] Self-Driving Cars: Multimodal Integration
[23:41] Processing data with Transformers
[26:46] Real-time phone data gathering
[30:49] Real-time observability in AI
[35:09] Time to first token
[37:26] Preferred vs. Dynamic Model Selection
[40:12] Event-driven architecture basics
[42:06] Navigating challenges together
[44:02] Challenges with Inconsistent Responses
[45:40] Importance of product reliability
[47:47] Training Data and Model Performance
[50:02] Exploring AI in Customer Service
[51:34] Navigating challenges in AI
[53:15] Excited Launch Strategy Advice
[57:10] Wrap up
Get the Snipd podcast app
Unlock the knowledge in podcasts with the podcast player of the future.
AI-powered podcast player
Listen to all your favourite podcasts with AI-powered features
Discover highlights
Listen to the best highlights from the podcasts you love and dive into the full episode
Save any moment
Hear something you like? Tap your headphones to save it with AI-generated key takeaways
Share & Export
Send highlights to Twitter, WhatsApp or export them to Notion, Readwise & more
AI-powered podcast player
Listen to all your favourite podcasts with AI-powered features
Discover highlights
Listen to the best highlights from the podcasts you love and dive into the full episode