Coder Radio

Mike sits down with renowned open-source and COSMIC DE contributer Bryan Hyland to discuss working on projects for Linux-forward companies and of course some Rust! Bryan's Site Bryan on LinkedIn Mike on LinkedIn Coder Radio on Discord The Mad Botter Inc Mike's Book Mike's Blog

Scott on LinkedIn Black Dog Ventures Mike on LinkedIn Coder Radio on Discord The Mad Botter Inc Alice Limited Offer Mike's Book Mike's Blog

Mike on LinkedIn Coder Radio on Discord Mike's Oryx Review Alice Alice Jumpstart Offer

https://www.linkedin.com/in/brian-ogrady/ - my linkedin https://www.linkedin.com/company/qdrant/ - company linkedin https://qdrant.tech/contact-us - contact us https://github.com/qdrant/qdrant/ - Qdrant GH https://github.com/qdrant/qdrant-edge-demo - Qdrant Edge running on smart glasses Mike on LinkedIn Coder Radio on Discord Mike's Oryx Review Alice Alice Jumpstart Offer Vorpal Mike in USA Today

Jamie Taylor, a Microsoft MVP and open-source maintainer, built SpecKit to drive LLM-assisted development. He explains spec→plan→implement workflows, using constitutions to enforce project rules, onboarding brownfield repos, and applying OWASP security headers in ASP.NET Core. He also discusses multi-model support, task-driven TDD with agents, and practical limits like context windows and licensing.

Carmine Paolino, an author and developer with a focus on Ruby-based AI tooling, discusses his journey from rejecting PHP to embracing Ruby in 2009. He shares insights on building Chat With Work, highlighting its chat interface and workplace integrations. Carmine explains why he created RubyLLM, emphasizing its simplicity and unique features like provider adapters that allow switching models mid-conversation. He also reflects on Ruby’s developer ergonomics and shares his enthusiasm for a 3D printer and Codex CLI as essential tools.

ThousandEyes Murtaza on LinkedIn Internet Outages Map ThousandEyesJob Openings Mike on LinkedIn Coder Radio on Discord Alice Mike's 2026 Predictions Post Alice Jumpstart Offer

Mike's Year End Post Mike on LinkedIn Mike's Blog Show on Discord Alice Promo Dreamcast assorted references: Dreamcast overview https://sega.fandom.com/wiki/Dreamcast History of Dreamcast development https://segaretro.org/History_of_the_Sega_Dreamcast/Development The Rise and Fall of the Dreamcast: A Legend Gone Too Soon (Simon Jenner) https://sabukaru.online/articles/he-rise-and-fall-of-the-dreamcast-a-legend-gone-too-soon The Legacy of the Sega Dreamcast | 20 Years Later https://medium.com/@Amerinofu/the-legacy-of-the-sega-dreamcast-20-years-later-d6f3d2f7351c Socials & Plugs The R Podcast https://r-podcast.org/ R Weekly Highlights https://serve.podhome.fm/r-weekly-highlights Shiny Developer Series https://shinydevseries.com/ Eric on Bluesky https://bsky.app/profile/rpodcast.bsky.social Eric on Mastodon https://podcastindex.social/@rpodcast Eric on LinkedIn https://www.linkedin.com/in/eric-nantz-6621617/

Links James on LinkedIn Mike on LinkedIn Mike's Blog Show on Discord Alice Promo AI on Red Hat Enterprise Linux (RHEL) Trust and Stability: RHEL provides the mission-critical foundation needed for workloads where security and reliability cannot be compromised. Predictive vs. Generative: Acknowledging the hype of GenAI while maintaining support for traditional machine learning algorithms. Determinism: The challenge of bringing consistency and security to emerging AI technologies in production environments. Rama-Llama & Containerization Developer Simplicity: Rama-Llama helps developers run local LLMs easily without being "locked in" to specific engines; it supports Podman, Docker, and various inference engines like Llama.cpp and Whisper.cpp. Production Path: The tool is designed to "fade away" after helping package the model and stack into a container that can be deployed directly to Kubernetes. Behind the Firewall: Addressing the needs of industries (like aircraft maintenance) that require AI to stay strictly on-premises. Enterprise AI Infrastructure Red Hat AI: A commercial product offering tools for model customization, including pre-training, fine-tuning, and RAG (Retrieval-Augmented Generation). Inference Engines: James highlights the difference between Llama.cpp (for smaller/edge hardware) and vLLM, which has become the enterprise standard for multi-GPU data center inferencing.

Tabnine Eran on LinkedIn Alice for Snowflake Mike on X Coder on X Show Discord Alice & Custom Dev