<![CDATA[The AI Engineering Podcast]]>https://the-ai-engineering-podcas-yw7ssl.jellypod.comPowered by Jellypod (https://www.jellypod.com)Sat, 18 Jul 2026 04:49:03 GMTTue, 14 Jul 2026 23:46:06 GMTyes365f3031-710f-4429-b0b8-538b599343b0JellypodA highly-technical, daily show covering all that happened in the world of AI Engineering. Curated from around the internet, powered by Jellypod.A highly-technical, daily show covering all that happened in the world of AI Engineering. Curated from around the internet, powered by Jellypod.episodicJellypodfeed+81e00646@podcasts.jellypod.comfalse<![CDATA[Why Kubernetes Fails AI Agents]]>https://the-ai-engineering-podcas-yw7ssl.jellypod.com/episodes/1097a8f1-013c-42a3-93ac-4712fd0fd70e1097a8f1-013c-42a3-93ac-4712fd0fd70eSat, 18 Jul 2026 04:38:51 GMT6This episode breaks down why Docker and Kubernetes are the wrong fit for AI agents, from container breakout risks to the pain of stateless restarts and slow recovery. It then explores how MicroVMs, NVMe caching, and copy-on-write overlays enable fast, secure sandboxing with sub-second backtracking.

]]>JellypodThis episode breaks down why Docker and Kubernetes are the wrong fit for AI agents, from container breakout risks to the pain of stateless restarts and slow recovery. It then explores how MicroVMs, NVMe caching, and copy-on-write overlays enable fast, secThis episode breaks down why Docker and Kubernetes are the wrong fit for AI agents, from container breakout risks to the pain of stateless restarts and slow recovery. It then explores how MicroVMs, NVMe caching, and copy-on-write overlays enable fast, secure sandboxing with sub-second backtracking.false00:00:55full<![CDATA[Kimi K3: The Open-Weights Giant Taking Over Frontend Coding]]>https://the-ai-engineering-podcas-yw7ssl.jellypod.com/episodes/e6fba41a-dcfc-4f2e-a849-11367664570fe6fba41a-dcfc-4f2e-a849-11367664570fFri, 17 Jul 2026 01:53:11 GMT5We break down Moonshot AI’s Kimi K3, the 2.8-trillion-parameter open-weights giant that shot to the top of the Frontend Code Arena while only landing mid-pack in general chat. Plus: why its vision-in-the-loop coding workflow, prompt caching economics, and massive latent MoE architecture make it both a breakthrough and a local-running nightmare.

]]>JellypodWe break down Moonshot AI’s Kimi K3, the 2.8-trillion-parameter open-weights giant that shot to the top of the Frontend Code Arena while only landing mid-pack in general chat. Plus: why its vision-in-the-loop coding workflow, prompt caching economics, andWe break down Moonshot AI’s Kimi K3, the 2.8-trillion-parameter open-weights giant that shot to the top of the Frontend Code Arena while only landing mid-pack in general chat. Plus: why its vision-in-the-loop coding workflow, prompt caching economics, and massive latent MoE architecture make it both a breakthrough and a local-running nightmare.false00:07:13full<![CDATA[Levitating Labs, Reasoning Tokens, and the Future of Discovery]]>https://the-ai-engineering-podcas-yw7ssl.jellypod.com/episodes/3cf636af-ac28-489e-8758-a7764c61b9493cf636af-ac28-489e-8758-a7764c61b949Thu, 16 Jul 2026 13:37:44 GMT4This episode explores how Lila Sciences is turning the lab into a data center, using automated hardware, legacy instruments, and iterative physical feedback to accelerate discovery. It also dives into generalist AI, reward hacking in wet-lab experiments, and why biology and materials science may be the next great frontier for scientific intelligence.

]]>JellypodThis episode explores how Lila Sciences is turning the lab into a data center, using automated hardware, legacy instruments, and iterative physical feedback to accelerate discovery. It also dives into generalist AI, reward hacking in wet-lab experiments, This episode explores how Lila Sciences is turning the lab into a data center, using automated hardware, legacy instruments, and iterative physical feedback to accelerate discovery. It also dives into generalist AI, reward hacking in wet-lab experiments, and why biology and materials science may be the next great frontier for scientific intelligence.false00:08:19full<![CDATA[Mira Murati’s Open-Weight Giant and the Rise of Machine Shorthand]]>https://the-ai-engineering-podcas-yw7ssl.jellypod.com/episodes/af8c4a3f-e97f-4cf8-9968-c89c10268b72af8c4a3f-e97f-4cf8-9968-c89c10268b72Thu, 16 Jul 2026 06:25:02 GMT3We unpack Thinking Machines Lab’s massive open-weight model release, from its trillion-scale Mixture-of-Experts architecture and local deployment support to what it means for developer sovereignty. Then we dive into the model’s eerie self-generated reasoning language and the self-tuning demo that raises big questions about transparency, monitoring, and AI building AI.

]]>JellypodWe unpack Thinking Machines Lab’s massive open-weight model release, from its trillion-scale Mixture-of-Experts architecture and local deployment support to what it means for developer sovereignty. Then we dive into the model’s eerie self-generated reasonWe unpack Thinking Machines Lab’s massive open-weight model release, from its trillion-scale Mixture-of-Experts architecture and local deployment support to what it means for developer sovereignty. Then we dive into the model’s eerie self-generated reasoning language and the self-tuning demo that raises big questions about transparency, monitoring, and AI building AI.false00:05:57full<![CDATA[From Code Erosion to Self-Healing Bricks]]>https://the-ai-engineering-podcas-yw7ssl.jellypod.com/episodes/7a77bc9d-93ad-4b1e-b253-bc74b938f4347a77bc9d-93ad-4b1e-b253-bc74b938f434Wed, 15 Jul 2026 00:00:39 GMT2This episode explores why today’s AI coding agents need endurance testing, better tracing, and dynamic web evaluations to survive real-world production workflows. It also dives into active perception in multimodal models, ultra-low-bit local models, and Sakana AI’s self-organizing physical brick system.

]]>JellypodThis episode explores why today’s AI coding agents need endurance testing, better tracing, and dynamic web evaluations to survive real-world production workflows. It also dives into active perception in multimodal models, ultra-low-bit local models, and SThis episode explores why today’s AI coding agents need endurance testing, better tracing, and dynamic web evaluations to survive real-world production workflows. It also dives into active perception in multimodal models, ultra-low-bit local models, and Sakana AI’s self-organizing physical brick system.false00:07:28full<![CDATA[GPT-5.6 Variants, Ultra Mode, and the Harness Battle]]>https://the-ai-engineering-podcas-yw7ssl.jellypod.com/episodes/e85e1564-9266-4acd-afb4-3d15b1dcd95de85e1564-9266-4acd-afb4-3d15b1dcd95dTue, 14 Jul 2026 23:55:32 GMT1We dig into the chaos of GPT-5.6’s 36 configuration variants, why cheaper models can outperform pricier tiers with the right reasoning settings, and how endless parameter tuning is slowing teams down.

Then we break down the dangerous cost traps in ultra mode, why subagents can accidentally inherit premium settings, and why the real moat is shifting from model weights to the execution harness.

]]>JellypodWe dig into the chaos of GPT-5.6’s 36 configuration variants, why cheaper models can outperform pricier tiers with the right reasoning settings, and how endless parameter tuning is slowing teams down. Then we break down the dangerous cost traps in ultra mWe dig into the chaos of GPT-5.6’s 36 configuration variants, why cheaper models can outperform pricier tiers with the right reasoning settings, and how endless parameter tuning is slowing teams down. Then we break down the dangerous cost traps in ultra mode, why subagents can accidentally inherit premium settings, and why the real moat is shifting from model weights to the execution harness.false00:04:16full