{"podcast":{"title":"Latent Space: The AI Engineer Podcast","slug":"latent-space-ai-engineer","podcast_index_feed_id":6058902,"rss_url":"https://api.substack.com/feed/podcast/1084089.rss","website_url":"https://www.latent.space/podcast","image_url":"https://substackcdn.com/feed/podcast/1084089/ca7468da5614a246d2906ee8926f6de7.jpg","author":"Latent.Space","episode_count":217,"summary":"The AI Engineer newsletter + Top technical AI podcast. How leading labs build Agents, Models, Infra, & AI for Science. See https://latent.space/about for highlights from Greg Brockman, Andrej Karpathy, George Hotz, Simon Willison, Soumith Chintala et al!","last_synced_at":"2026-08-02T15:06:40.969607+00:00","page_url":"https://stenobird.com/podcast/latent-space-ai-engineer"},"episode":{"title":"Inside the Model Factory — Eiso Kant, Poolside AI","slug":"inside-the-model-factory-eiso-kant-poolside-ai","published_at":"2026-07-23T05:09:14+00:00","page_url":"https://stenobird.com/podcast/latent-space-ai-engineer/inside-the-model-factory-eiso-kant-poolside-ai","show_page_url":"https://stenobird.com/podcast/latent-space-ai-engineer","url":"https://www.latent.space/p/poolside","audio_url":"https://api.substack.com/feed/podcast/208082176/eb710305543a96a17ff4f67800586d98.mp3","summary":"Poolside AI co-founder Eiso Kant reveals how they built a 'Model Factory' capable of running 20,000 experiments per month to produce high-performance small models. The discussion explores the engineering behind Laguna S, the shift from tool-calling to code-writing agents, and why efficiency beats raw scale.","meta_description":"Learn how Poolside AI uses a high-velocity Model Factory to build efficient, open-weight models that outperform much larger competitors.","key_points":["Main idea: The 'Model Factory' approach prioritizes reproducible experimentation and massive-scale ablation over manual tuning","Practical takeaway: Efficiency in smaller models can outperform much larger architectures through better data pipelines and training precision","Failure mode: Relying on massive, unverified datasets without rigorous internal evaluation and 'dogfooding' leads to wasted compute","Technical shift: The industry is moving from static tool-calling to models that natively write and execute scripts to solve complex tasks","Strategic vision: A decentralized ecosystem of 100 foundation model companies is more resilient and innovative than an oligopoly of five"],"chapters":[{"start_ms":60000,"title":"The Karpathy Influence","summary":"Eiso discusses how Andrej Karpathy's work on RNNs inspired a decade-long bet on neural networks for code generalization."},{"start_ms":600000,"title":"The Value of Technical Transparency","summary":"Why detailed technical reports and open research are essential for the progress of the AI ecosystem."},{"start_ms":1080000,"title":"Inside the Model Factory","summary":"An exploration of the infrastructure required to manage tens of thousands of monthly experiments and continuous data streaming."},{"start_ms":1620000,"title":"From YOLO Runs to Rigorous Science","summary":"The transition from early-stage 'wild west' experimentation to a structured, ablation-focused engineering culture."},{"start_ms":2640000,"title":"The Future of Reasoning in Training","summary":"Discussing the potential of introducing reasoning, verification, and backtracking earlier in the pre-training phase."},{"start_ms":3720000,"title":"The End of Tool-Calling","summary":"Why the next generation of models will replace complex system prompts and tool definitions with native code execution."},{"start_ms":6840000,"title":"High-Agency Engineering","summary":"How small, mission-driven teams can achieve massive individual impact in the era of frontier model development."}],"topics":["Poolside AI","Model Factory","LLM Training","Machine Learning Engineering","Open Weights","Code Generation","AGI","Inference Optimization"],"duration_seconds":6873,"processing_state":"processed","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/latent-space-ai-engineer/episodes/inside-the-model-factory-eiso-kant-poolside-ai/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/latent-space-ai-engineer/inside-the-model-factory-eiso-kant-poolside-ai.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]}}