{"podcast":{"title":"The TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence)","slug":"twiml-ai-podcast","podcast_index_feed_id":1045879,"rss_url":"https://feeds.megaphone.fm/MLN2155636147","website_url":"https://twimlai.com","image_url":"https://megaphone.imgix.net/podcasts/35230150-ee98-11eb-ad1a-b38cbabcd053/image/TWIML_AI_Podcast_Official_Cover_Art_1400px.png?ixlib=rails-4.3.1&max-w=3000&max-h=3000&fit=crop&auto=format,compress","author":"TWIML","episode_count":785,"summary":"Machine learning and artificial intelligence are dramatically changing the way businesses operate and people live. The TWIML AI Podcast brings the top minds and ideas from the world of ML and AI to a broad and influential community of ML/AI researchers, data scientists, engineers and tech-savvy business and IT leaders. Hosted by Sam Charrington, a sought after industry analyst, speaker, commentator and thought leader. Technologies covered include machine learning, artificial intelligence, deep learning, natural language processing, neural networks, analytics, computer science, data science and more.","last_synced_at":null,"page_url":"https://stenobird.com/podcast/twiml-ai-podcast"},"episode":{"title":"The Evolution of Reasoning in Small Language Models with Yejin Choi - #761","slug":"the-evolution-of-reasoning-in-small-language-models-with-yejin-choi-761","published_at":"2026-01-29T21:48:00+00:00","page_url":"https://stenobird.com/podcast/twiml-ai-podcast/the-evolution-of-reasoning-in-small-language-models-with-yejin-choi-761","show_page_url":"https://stenobird.com/podcast/twiml-ai-podcast","url":"https://twimlai.com/podcast/twimlai/the-evolution-of-reasoning-in-small-language-models/","audio_url":"https://pscrb.fm/rss/p/traffic.megaphone.fm/MLN2256483849.mp3?updated=1769723982","summary":"Yejin Choi explores how high-quality data curation and algorithmic innovations like 'Prismatic Synthesis' can bridge the intelligence gap between small and large language models. The discussion highlights the necessity of democratizing AI to prevent an 'artificial hivemind' and ensure models reflect diverse human values.","meta_description":"Yejin Choi discusses making small language models reason better through synthetic data, reinforcement learning, and the importance of pluralistic alignmen…","key_points":["Main idea: Small language models can achieve high reasoning capabilities through superior data quality and diverse synthetic generation rather than just scale","Practical takeaway: Using reinforcement learning as a pre-training objective can incentivize models to 'think' before predicting tokens","Failure mode: Post-training and RL can lead to 'mode collapse' or an 'artificial hivemind,' where model outputs become dangerously homogeneous","Technical innovation: The 'Prismatic Synthesis' method uses gradient-based approaches to generate diverse math data while filtering overrepresented examples","Societal mission: AI alignment must move toward 'pluralistic alignment' to ensure models can steer between diverse, socially acceptable value systems"],"chapters":[{"start_ms":60000,"title":"Introduction to Yejin Choi","summary":"An introduction to Yejin Choi's work at Stanford and her focus on reasoning in small language models."},{"start_ms":355000,"title":"The Case for Small Language Models","summary":"Discussing the importance of avoiding industry-wide homogeneity and the potential of scaling intelligence in smaller architectures."},{"start_ms":645000,"title":"Synthetic Data and Reasoning","summary":"Exploring how automatic synthetic data generation and expert data curation drive model intelligence."},{"start_ms":940000,"title":"Reinforcement Learning Challenges","summary":"The risks of reinforcement learning, including issues like code-switching and loss of coherence in math problems."},{"start_ms":1220000,"title":"The Risk of Model Homogeneity","summary":"Analyzing how sequential fine-tuning and RL can reduce output diversity and lead to predictable, repetitive model behavior."},{"start_ms":1515000,"title":"The Artificial Hivemind","summary":"Examining the societal implications of AI models converging on a single, non-diverse way of thinking."},{"start_ms":1830000,"title":"Democratizing AI Development","summary":"The need for non-profit and academic participation to ensure AI serves all of humanity, not just large corporations."},{"start_ms":2135000,"title":"Prismatic Synthesis Algorithm","summary":"A deep dive into the Prismatic algorithm for generating diverse, high-quality synthetic math datasets."}],"topics":["Small Language Models","Reasoning","Synthetic Data","Reinforcement Learning","AI Alignment","Prismatic Synthesis","Artificial Intelligence","Machine Learning"],"duration_seconds":3981,"processing_state":"processed","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/twiml-ai-podcast/episodes/the-evolution-of-reasoning-in-small-language-models-with-yejin-choi-761/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/twiml-ai-podcast/the-evolution-of-reasoning-in-small-language-models-with-yejin-choi-761.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]}}