{"podcast":{"title":"Data Science at Home","slug":"data-science-at-home-952409","podcast_index_feed_id":952409,"rss_url":"https://datascienceathome.podbean.com/feed.xml","website_url":"https://datascienceathome.podbean.com","image_url":"https://pbcdn1.podbean.com/imglogo/image-logo/1799802/dsh-cover-2.jpg","author":"Francesco Gadaleta","episode_count":316,"summary":"Cutting through AI bullsh*t","last_synced_at":"2026-07-20T22:19:59.485660+00:00","page_url":"https://stenobird.com/podcast/data-science-at-home-952409"},"episode":{"title":"From Tokens to Vectors: The Efficiency Hack That Could Save AI (Ep. 294)","slug":"from-tokens-to-vectors-the-efficiency-hack-that-could-save-ai-ep-294","published_at":"2025-11-11T08:58:13+00:00","page_url":"https://stenobird.com/podcast/data-science-at-home-952409/from-tokens-to-vectors-the-efficiency-hack-that-could-save-ai-ep-294","show_page_url":"https://stenobird.com/podcast/data-science-at-home-952409","url":"https://datascienceathome.podbean.com/e/from-tokens-to-vectors-the-efficiency-hack-that-could-save-ai-ep-294/","audio_url":"https://mcdn.podbean.com/mf/web/3bymn4anxg76um4n/calm-podcast-final.mp3","summary":"LLMs generate text painfully slow, one low-info token at a time. Researchers just figured out how to compress 4 tokens into smart vectors & cut costs by 44%—with full code & proofs! Meanwhile OpenAI drops product ads, not papers. We explore CALM & why open science matters. 🔥📊 Sponsors This episode is brought to you by Statistical Horizons At Statistical Horizons, you can stay ahead with expert-led livestream seminars that make data analytics and AI methods practical and accessible.Join thousands of researchers and professionals who’ve advanced their careers with Statistical Horizons.Get $200 off any seminar with code DATA25 at https://statisticalhorizons.com","meta_description":"LLMs generate text painfully slow, one low-info token at a time. Researchers just figured out how to compress 4 tokens into smart vectors & cut costs…","key_points":[],"chapters":[],"topics":[],"duration_seconds":2814,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/data-science-at-home-952409/episodes/from-tokens-to-vectors-the-efficiency-hack-that-could-save-ai-ep-294/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/data-science-at-home-952409/from-tokens-to-vectors-the-efficiency-hack-that-could-save-ai-ep-294.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]}}