Go offline with the Player FM app!
047: The anatomy of a voice assistant, part 3 - Large language models (LLMs)
Manage episode 438398417 series 3533896
It's the third in a series of technical deep dives for building IVAs, and for this episode, it's all about LLMs. Kylie chats with Shawn Wen, co-founder and CTO at PolyAI, who explains why LLMs can accomplish 70% of what’s needed for voice assistants, and more importantly: what's involved in the remaining 30%. The discussion touches on strategies to manage challenges through prompt engineering, dialogue management, and integrating third-party APIs, while highlighting the similarities between AI and human behavior. A look into cybersecurity and the future of specialized LLMs rounds out the conversation, offering insights for industry professionals navigating this evolving technology.
Follow PolyAI on LinkedIn
Watch this and other episodes of the Deep Learning pod on YouTube
75 episodes
Manage episode 438398417 series 3533896
It's the third in a series of technical deep dives for building IVAs, and for this episode, it's all about LLMs. Kylie chats with Shawn Wen, co-founder and CTO at PolyAI, who explains why LLMs can accomplish 70% of what’s needed for voice assistants, and more importantly: what's involved in the remaining 30%. The discussion touches on strategies to manage challenges through prompt engineering, dialogue management, and integrating third-party APIs, while highlighting the similarities between AI and human behavior. A look into cybersecurity and the future of specialized LLMs rounds out the conversation, offering insights for industry professionals navigating this evolving technology.
Follow PolyAI on LinkedIn
Watch this and other episodes of the Deep Learning pod on YouTube
75 episodes
All episodes
×
1 076: AI rollups: all VC sizzle and no stake? Thoughts from a recent Fortune article. 22:38

1 075: Human agent & AI cohesion in the contact center. What will it take? 23:11

1 074: AI and the State of Financial Services 20:11

1 073: What are everyday people using LLMs for, really? 21:52

1 072: Introducing Owl: PolyAI's in-house speech recognition model 21:46

1 071: Differentiation in a generative AI era 20:14

1 070: The journey from digital-first to AI-first, and how to do it right 24:03

1 069: Announcing Agent Studio, the world's only voice-first conversational AI platform 19:53

1 068: DOGE bites federal phone lines. Are Elon & Co. shutting down toll-free? 16:46

1 067: Sonnet 3.7 + Orion, AWS goes agentic & the US Patent Office sets rules 20:30

1 066: The anatomy of telephony, part 3 - Predictions 17:14

1 065: The anatomy of telephony, part 2 - Evolution 22:06

1 064: The anatomy of telephony, part 1 - Origins 23:06

1 063: Surprising findings from PolyAI's recent CS trends report 25:02

1 062: AI's Sputnik moment? DeepSeek R1 has entered the chat(GPT). 18:47
Welcome to Player FM!
Player FM is scanning the web for high-quality podcasts for you to enjoy right now. It's the best podcast app and works on Android, iPhone, and the web. Signup to sync subscriptions across devices.