エピソード

  • Gone in 9 Seconds: When Claude Code Goes Rogue

    Gone in 9 Seconds: When Claude Code Goes Rogue
    2026/05/01
    This episode explores a critical incident where an AI agent, powered by Claude, accidentally wiped an entire company's production database by literally interpreting an underspecified command and possessing excessive permissions. It also reviews recent updates to AI coding tools such as GitHub Copilot, Google Gemini, and OpenAI's Code Interpreter, highlighting their evolving capabilities. Listeners will learn about the crucial importance of precise prompt engineering, setting explicit boundaries, and carefully managing permissions for AI agents to prevent similar destructive outcomes, while also understanding current advancements in AI development.
    続きを読む 一部表示
    11 分
  • The $2,400 ROI Reality Check: Claude Code, Cursor, and Copilot

    The $2,400 ROI Reality Check: Claude Code, Cursor, and Copilot
    2026/05/01
    This episode explores recent advancements in AI coding tools, detailing updates from OpenAI Codex, Anthropic Claude Code, Google Gemini Code Assist, GitHub Copilot X, and Cursor, which focus on enhanced multi-file context, broader integrations, and new interaction models. It then introduces a unique, year-long real-world evaluation of Claude Code, Cursor, and GitHub Copilot, revealing their distinct strengths, such as Copilot's efficiency for boilerplate and Claude Code's prowess in complex logic. Listeners will gain insight into how these tools perform under sustained pressure and their true practical value beyond marketing claims.
    続きを読む 一部表示
    14 分
  • The Zero-Capability Exploit: How a Single Keystroke Broke AI’s Gold Standard

    The Zero-Capability Exploit: How a Single Keystroke Broke AI’s Gold Standard
    2026/05/01
    This episode explores a critical "Zero-Capability Exploit" that allows a single character to bypass AI evaluation benchmarks, revealing a fundamental vulnerability in how AI capabilities are measured. It also provides a comprehensive update on the AI tooling landscape, detailing recent advancements from major players like OpenAI, Anthropic, Google, and GitHub Copilot, alongside innovations from upstarts like Cursor and Windsurf. Listeners will gain insights into both the fragility of current AI evaluation and the strategic evolution of AI development tools.
    続きを読む 一部表示
    14 分
  • The IDE is Dead, Long Live the Terminal: Inside the $12.8B AI Coding Shift

    The IDE is Dead, Long Live the Terminal: Inside the $12.8B AI Coding Shift
    2026/05/01
    This episode explores recent advancements in AI coding tools from major players like OpenAI, Anthropic, and Google, detailing new features and their impact on developer workflows. It also addresses the provocative claim that the traditional Integrated Development Environment (IDE) is effectively "dead," discussing how AI agents and the terminal are redefining the software development landscape. Listeners will learn about current trends in AI-assisted coding and the evolving role of development environments.
    続きを読む 一部表示
    14 分
  • The 8% Reality Check: Why AI Coding Tools Aren't Delivering 10x Engineers (Yet)

    The 8% Reality Check: Why AI Coding Tools Aren't Delivering 10x Engineers (Yet)
    2026/04/30
    This episode explores a landmark study revealing a modest 8% increase in developer output despite widespread AI tool adoption, challenging the '10x developer' narrative. It details how this 'expectation gap' is driving a fundamental shift among AI toolmakers, moving from individual coding assistance to systemic, autonomous agent-based orchestration. Listeners will learn about new platforms like Cursor 3, Anthropic's Claude Code, and Cognition AI's Devin, which are transforming into operating systems for digital workers and autonomous infrastructure components.
    続きを読む 一部表示
    16 分
  • Inside the Claude Code "Lobotomy": How a Caching Bug Broke Agentic Memory

    Inside the Claude Code "Lobotomy": How a Caching Bug Broke Agentic Memory
    2026/04/25
    This episode explores the Anthropic Claude Code "lobotomy" incident, revealing that perceived degradation stemmed from scaffolding failures rather than the core AI model itself. It then covers rapid-fire updates on the AI tooling landscape, including Meta's strategic bet on CPU compute for agentic AI, OpenAI's "Trusted Access for Cyber" program for un-nerfed models, and Google's shift to a multi-model cloud strategy, offering listeners insights into the evolving infrastructure and deployment challenges in the AI space.
    続きを読む 一部表示
    16 分
  • Colossus and Code: Unpacking the $60 Billion SpaceX/Cursor Megadeal

    Colossus and Code: Unpacking the $60 Billion SpaceX/Cursor Megadeal
    2026/04/25
    This episode explores SpaceX's audacious $60 billion option to acquire the code editor Cursor, framing it within the context of future AI development and SpaceX's IPO. It delves into the rapidly evolving AI coding tool landscape, highlighting advancements from OpenAI's Codex, GitHub Copilot's move towards autonomous code review, and Google's efforts to unify its internal AI tools. Listeners will learn about the paradoxical state of developer trust in AI-generated code, where high usage contrasts with low confidence for production, emphasizing the critical need for verifiable code integrity.
    続きを読む 一部表示
    15 分
  • Shattering SWE-bench: The Claude Mythos 93.9% Leap & The End of Text-Only Coding

    Shattering SWE-bench: The Claude Mythos 93.9% Leap & The End of Text-Only Coding
    2026/04/20
    This episode explores the nuanced reality behind Anthropic's Claude Mythos achieving a 93.9% score on SWE-bench, revealing it's not the definitive 'AI codes itself' moment it appears to be. Listeners will learn about the significant market correction in AI coding economics, the rise of 'agentic compute' models, and how new visual AI capabilities and tools like GitHub Copilot Workspace are transforming the entire software development lifecycle from design to project management.
    続きを読む 一部表示
    18 分