{"podcast":{"title":"MLOps Weekly Podcast","slug":"mlops-weekly","podcast_index_feed_id":5487202,"rss_url":"https://media.rss.com/mlops-weekly/feed.xml","website_url":"https://rss.com/podcasts/mlops-weekly","image_url":"https://media.rss.com/mlops-weekly/20220607_010653_39e23ec13c42d0efa239e27bf455ceed.jpg","author":"Simba Khadder","episode_count":32,"summary":"Join each week as we talk to MLOps operators, practitioners, and professionals about the current state of MLOps.","last_synced_at":null,"page_url":"https://stenobird.com/podcast/mlops-weekly"},"episode":{"title":"MLOps Week 18: The LLM Revolution & the Future of Data with Josh Wills","slug":"mlops-week-18-the-llm-revolution-the-future-of-data-with-josh-wills","published_at":"2023-05-24T15:37:13+00:00","page_url":"https://stenobird.com/podcast/mlops-weekly/mlops-week-18-the-llm-revolution-the-future-of-data-with-josh-wills","show_page_url":"https://stenobird.com/podcast/mlops-weekly","url":"https://rss.com/podcasts/mlops-weekly/966178","audio_url":"https://content.rss.com/episodes/132586/966178/mlops-weekly/2023_05_24_15_36_48_de6a6a90-4335-4dff-a632-ca6d985881f9.mp3","summary":"Josh Wills shares lessons from scaling data pipelines at Slack and Google, focusing on the necessity of data contracts. The discussion explores whether LLMs represent a fundamental shift like electricity or a functional shift like the mobile phone.","meta_description":"Former Slack and Google engineer Josh Wills discusses data contracts, the engineering challenges of massive-scale indexing, and the true hype of LLMs.","key_points":["Main idea: Data contracts are essential for decoupling production systems from downstream data warehouses","Practical takeaway: Treat data pipelines as production-grade software by implementing integration tests between upstream and downstream systems","Failure mode: Over-identifying with source code can lead to professional burnout and resistance to necessary code reviews","Main idea: The future of LLMs likely depends on whether the economics favor a single dominant model or a fragmented ecosystem of specialized models","Practical takeaway: In high-scale environments, prepare for 'one-in-a-trillion' edge cases that become frequent when processing trillions of records"],"chapters":[{"start_ms":60000,"title":"The Mount Everest of Data Engineering","summary":"Reflecting on the technical and human challenges of rebuilding Slack's massive search indexing pipeline."},{"start_ms":260000,"title":"Implementing Data Contracts","summary":"How using Thrift schemas to tie production systems to the data warehouse prevents downstream breakage."},{"start_ms":1100000,"title":"The Hype Cycle of LLMs","summary":"Evaluating whether Large Language Models are a paradigm shift akin to the mobile phone or the invention of electricity."},{"start_ms":1305000,"title":"Lessons from Google and Go","summary":"A look at the adoption of the Go programming language and the importance of tools fitting the community's needs."},{"start_ms":1525000,"title":"The Middle Ground of AI Hype","summary":"Navigating the space between extreme skepticism and the 'electricity-level' hype of generative AI."},{"start_ms":2140000,"title":"The Economics of Model Training","summary":"Discussing the scarcity of GPUs and the business incentives for platforms like Databricks to support decentralized model training."}],"topics":["Data Engineering","LLMs","Data Contracts","MLOps","Scalable Systems","Data Warehousing","Artificial Intelligence","GPU Scarcity"],"duration_seconds":2773,"processing_state":"processed","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/mlops-weekly/episodes/mlops-week-18-the-llm-revolution-the-future-of-data-with-josh-wills/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/mlops-weekly/mlops-week-18-the-llm-revolution-the-future-of-data-with-josh-wills.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]}}