{"podcast":{"title":"Vanishing Gradients","slug":"vanishing-gradients-4989163","podcast_index_feed_id":4989163,"rss_url":"https://api.substack.com/feed/podcast/2632531.rss","website_url":"https://hugobowne.substack.com/podcast","image_url":"https://substackcdn.com/feed/podcast/2632531/e8d57d9d781f20857949c2678ef8c9c2.jpg","author":"Hugo Bowne-Anderson","episode_count":77,"summary":"a data podcast with hugo bowne-anderson","last_synced_at":null,"page_url":"https://stenobird.com/podcast/vanishing-gradients-4989163"},"episode":{"title":"Episode 66: The Agent Paradox - Why Moderna's Most Productive AI Systems Aren't Agents","slug":"episode-66-the-agent-paradox-why-moderna-s-most-productive-ai-systems-aren-t-agents","published_at":"2026-01-08T06:44:05+00:00","page_url":"https://stenobird.com/podcast/vanishing-gradients-4989163/episode-66-the-agent-paradox-why-moderna-s-most-productive-ai-systems-aren-t-agents","show_page_url":"https://stenobird.com/podcast/vanishing-gradients-4989163","url":"https://hugobowne.substack.com/p/episode-66-the-agent-paradox-why","audio_url":"https://api.substack.com/feed/podcast/183508684/ec331649467a048117a9819b485ac919.mp3","summary":"Surprise. We don’t have agents . I actually went in and did an audit of all the LLM applications that we’ve developed internally. And if you were to take Anthropic’s definition of workflow versus agent , we don’t have agents. I would not classify any of our applications as agents. x Eric Ma , who leads Research Data Science in the Data Science and AI group at Moderna , joins Hugo on moving past the hype of autonomous agents to build reliable, high-value workflows . We discuss: * Reliable Workflows : Prioritize rigid workflows over dynamic AI agents to ensure reliability and minimize stochasticity in production environments; * Permission Mapping : The true challenge in regulated environments is security , specifically mapping permissions across source documents, vector stores , and model weights ; * Trace Log Risk : LLM execution traces pose a regulatory risk , inadvertently leaking restricted data like trade secrets or personal information ; * High-Value Data Work : LLMs excel at transforming archived documents and freeform forms into required formats, offloading significant “janitorial” work from scientists; * “Non-LLM” First : Solve problems with simpler tools like Python or ML models before LLMs to ensure robustness and eliminate generative AI stochasticity ; * Contextual Evaluation : Tailor evaluation rigor to consequences ; low-stakes tools can be “vibe-checked,” while patient safety outputs demand exhaustive error characterization ; * Serverless Biotech Backbone : Serverless infrastructure like Modal and reactive notebooks such as Marimo empowers biotech data scientists for rapid deployment without heavy infrastructure overhead . You can also find the full episode on Spotify , Apple Podcasts , and YouTube . You can also interact directly with the transcript here…","meta_description":"Surprise. We don’t have agents . I actually went in and did an audit of all the LLM applications that we’ve developed internally. And if you were to take…","key_points":[],"chapters":[],"topics":[],"duration_seconds":2578,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/vanishing-gradients-4989163/episodes/episode-66-the-agent-paradox-why-moderna-s-most-productive-ai-systems-aren-t-agents/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/vanishing-gradients-4989163/episode-66-the-agent-paradox-why-moderna-s-most-productive-ai-systems-aren-t-agents.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]}}