About this episode
Send a textLarge language models are powerful tools — but why do they ramble on and on instead of just getting to the point?In this episode of Deep Learning with PolyAI, Nikola Mrkši? sits down with Oliver Shoulson, one of PolyAI’s original dialogue designers, to unpack why LLMs talk the way they do, and what that means for building natural-sounding voice AI.They dive into:Why LLMs are trained to over-explain, and how that breaks spoken dialogueThe subtle design choices that can make conversations feel human — without trying to fool anyoneThe debate over anthropomorphism: should AI agents admit they’re AI, or lean into human-like traits?How in-house LLMs can be fine-tuned to sound less like overeager interns and more like trustworthy teammatesVoice AI doesn’t need to trick us into thinking it’s human, but it does need to feel usable. This episode explores the hidden details of dialogue design that decide whether AI earns customer trust, or just frustrates them with endless rambling.? Watch the full conversation and learn more in Oliver's blog post about how to prevent your customer conversations from sounding like they're LLM slop: https://poly.ai/blog/how-not-to-talk-like-an-llm/?utm_source=youtube&utm_medium=podcast&utm_campaign=agenticai&utm_content=podcast#VoiceAI #LLM #Anthropomorphism #CustomerExperience #PolyAI Follow PolyAI on LinkedIn Watch this and other episodes of the Deep Learning pod on YouTube
