{"podcast":{"title":"AI Engineering Podcast","slug":"ai-engineering-podcast","podcast_index_feed_id":5875646,"rss_url":"https://serve.podhome.fm/rss/c9abdd38-a5dc-5eb2-96fd-f833f93208a7","website_url":"https://www.aiengineeringpodcast.com","image_url":"https://assets.podhome.fm/f6ff0caa-931b-4c08-bfdd-08dc7f5cd336/638557211890591941ai_engineering_podcast_logo.jpg","author":"Tobias Macey","episode_count":79,"summary":"This show is your guidebook to building scalable and maintainable AI systems. You will learn how to architect AI applications, apply AI to your work, and the considerations involved in building or customizing new models. Everything that you need to know to deliver real impact and value with machine learning and artificial intelligence.","last_synced_at":null,"page_url":"https://stenobird.com/podcast/ai-engineering-podcast"},"episode":{"title":"Inside the Black Box: Neuron-Level Control and Safer LLMs","slug":"inside-the-black-box-neuron-level-control-and-safer-llms","published_at":"2025-11-16T23:56:37+00:00","page_url":"https://stenobird.com/podcast/ai-engineering-podcast/inside-the-black-box-neuron-level-control-and-safer-llms","show_page_url":"https://stenobird.com/podcast/ai-engineering-podcast","url":"https://www.aiengineeringpodcast.com/explainability-interpretability-and-alignment-in-generative-ai-episode-69","audio_url":"https://op3.dev/e/dts.podtrac.com/redirect.mp3/serve.podhome.fm/episode/f6ff0caa-931b-4c08-bfdd-08dc7f5cd336/6389893367262785728b3436fd-d462-4756-90fe-f151f7317df5.mp3","summary":"Summary  In this episode of the AI Engineering Podcast Vinay Kumar, founder and CEO of Arya.ai and head of Lexsi Labs, talks about practical strategies for understanding and steering AI systems. He discusses the differences between interpretability and explainability, and why post-hoc methods can be misleading. Vinay shares his approach to tracing relevance through deep networks and LLMs using DL Backtrace, and how interpretability is evolving from an audit tool into a lever for alignment, enabling targeted pruning, fine-tuning, unlearning, and model compression. The conversation covers setting concrete alignment metrics, the gaps in current enterprise practices for complex models, and tailoring explainability artifacts for different stakeholders. Vinay also previews his team's \"AlignTune\" effort for neuron-level model editing and discusses emerging trends in AI risk, multi-modal complexity, and automated safety agents. He explores when and why teams should invest in interpretability and alignment, how to operationalize findings without overcomplicating evaluation, and the best practices for private, safer LLM endpoints in enterprises, aiming to make advanced AI not just accurate but also acceptable, auditable, and scalable.  Announcements  Hello and welcome to the AI Engineering Podcast, your guide to the fast-moving world of building scalable and maintainable AI systems When ML teams try to run complex workflows through traditional orchestration tools, they hit walls. Cash App discovered this with their fraud detection models - they needed flexible compute, isolated environments, and seamless data exchange between workflows, but their existing tools couldn't deliver. That's why Cash App rely on Prefect. Now their ML workflows run on whatever infrastruc…","meta_description":"Summary In this episode of the AI Engineering Podcast Vinay Kumar, founder and CEO of Arya.ai and head of Lexsi Labs, talks about practical strategi…","key_points":[],"chapters":[],"topics":[],"duration_seconds":3652,"processing_state":"processed","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/ai-engineering-podcast/episodes/inside-the-black-box-neuron-level-control-and-safer-llms/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/ai-engineering-podcast/inside-the-black-box-neuron-level-control-and-safer-llms.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]}}