Interview based show around AI Engineering. Episodes are also available as video on Youtube. Show notes have a summary and full transcript.
Episodes
22 Jun 2026
AI security challenges in large language models, such as data leakage and prompt injection, require adversarial testing, red teaming, tools like *Shade* and *Signal*, and structured frameworks to address integration risks, robustness gaps, and enterprise-specific security demands.
Open episode
3 Jun 2026
Formal verification is positioned as a critical tool for advancing AI by ensuring system correctness through mathematical rigor, exemplified by Axiom Math's achievements, tools like Lean, challenges in AI generalization, and the vision of AI as a "superhuman mathematician" through verified reasoning.
Open episode
3 Jun 2026
Strategic AI development shifts to ecosystem-driven frameworks prioritizing value creation, covering Microsoft's rigorous model training, agent-driven workflow management, real-world impact challenges, innovative business models, inclusive AI participation, and redefining work through agentic systems.
Open episode
2 Jun 2026
Advanced AI integration in developer workflows leverages tools like GitHub Copilot and agentic systems to automate tasks and boost productivity, while addressing challenges like skill bloat, security, open-source trust issues, and the shift to modular AI capabilities in enterprise and collaborative environments.
Open episode
1 Jun 2026
Advancements in AI research through community-driven knowledge sharing, challenges in scaling video models, technical innovations like vision transformers and diffusion models, and the integration of language models in generative media, alongside hurdles in training efficiency and sustainable development.
Open episode
28 May 2026
The evolution of AI agent development shifts toward autonomous workflows via tools like Devin for code generation and OpenInspect for cloud management, addressing growth, infrastructure challenges, security, scalability, enterprise adoption, open-source initiatives, diverse non-engineering use cases, and the role of human oversight in AI-native coding.
Open episode
27 May 2026
ESMC leverages transformer-based models trained on 6.8 billion protein sequences to predict structures, design functional proteins, and uncover evolutionary patterns through scalable, data-driven approaches, while balancing evolutionary constraints with interpretability and addressing limitations in data diversity and model generalizability.
Open episode
21 May 2026
A company evolved from pre-Docker browser-based IDEs and developer events to modern sandboxing platforms prioritizing AI agent infrastructure, leveraging bare-metal compute for scalability and addressing market demands with open-source strategies, spiky workloads, and future AI Cloud expansion amid GPU shortages.
Open episode
20 May 2026
Railway streamlines app deployment with AI-driven tools, environment cloning, and parallel testing, leveraging kernel patching and custom storage while addressing challenges like compute scarcity and AI agent coordination, alongside critiques of Git/GitHub and traditional software lifecycle practices.
Open episode
5 May 2026
AI is advancing theoretical physics by rapidly solving complex problems like quantum field theory calculations and simulating models such as SYK, though it still relies on human collaboration for original insights and contextual validation, reshaping research methodologies and education.
Open episode