Castuner

Context Window

A weekly look at the bleeding edge of AI coding tools — Claude Code, Codex, Cursor, Gemini, GitHub Copilot, and the upstarts chasing them.

Сайт подкаста

Слушайте в своём приложении

Эпизоды

35 эпизодов

  1. The IDE Wars: Interrogating the Cursor vs. Copilot Divide in Enterprise AI 11:22
  2. The Productivity Paradox: Why 30% More AI Code Equals Zero Extra Software 17:14
  3. The Case for Cheap AI: Why 'Cost Per Task' is Exposing the Frontier Premium 17:05
  4. The 80% Mirage: OpenAI's Audit and the Collapse of SWE-Bench Pro 8:35
  5. The Platform Always Wins: How GitHub Copilot Swallowed Claude Code 15:43
  6. The Token Trap: Uncovering the Hidden Costs of AI Coding at Scale 12:02
  7. Behind the Code: The $60 Billion Illusion of Choice in AI 7:50
  8. The End of Markdown and PwC’s 30,000-Seat Bet on the "Compute Allocator" 14:12
  9. The End of the "All You Can Eat" AI Buffet: Inside GitHub's Cost Crisis 11:19
  10. Unlocking the Black Box: Why the "Harness" is Quietly Killing the LLM Monopoly 17:24
  11. TrustFall: The Single Keystroke That Gives Hackers Root Access to Your Machine 11:27
  12. The Strategy Tax: Microsoft’s Internal Purge of Claude Code 13:04
  13. The Attack Surface Explosion: Putting a Leash on Semi-Autonomous Agents 14:50
  14. Systemic Failure: The ACM's Warning on "Vibe Coding" 11:49
  15. The Agentic Immune System: Why GitHub is Scanning Your MCP Server 14:48
  16. The 10-Second Disaster: When Cursor Met Production 13:20
  17. Gone in 9 Seconds: When Claude Code Goes Rogue 11:13
  18. The $2,400 ROI Reality Check: Claude Code, Cursor, and Copilot 13:41
  19. The Zero-Capability Exploit: How a Single Keystroke Broke AI’s Gold Standard 14:24
  20. The IDE is Dead, Long Live the Terminal: Inside the $12.8B AI Coding Shift 13:51
  21. The 8% Reality Check: Why AI Coding Tools Aren't Delivering 10x Engineers (Yet) 16:24
  22. Inside the Claude Code "Lobotomy": How a Caching Bug Broke Agentic Memory 16:03
  23. Colossus and Code: Unpacking the $60 Billion SpaceX/Cursor Megadeal 14:57
  24. Shattering SWE-bench: The Claude Mythos 93.9% Leap & The End of Text-Only Coding 18:25
  25. The Accidental Stack: Why the AI Coding Market Refuses to Consolidate 17:49
  26. The Copilot Data Grab and Microsoft's Quiet Pipeline 16:25
  27. The Complacency Trap: Are AI Agents Making Us Worse Developers? 17:52
  28. The Code Agent Orchestra: When Claude and Codex Start Talking 20:32
  29. The MCP Tax: Why Heavyweight AI Agents Are Going Broke (and Getting Dumber) 19:00
  30. The 30-Day Vibe Check: Real-World Friction in Claude Code, Cursor, and Copilot 19:46
  31. When AI Gets a Credit Card: The Dawn of Agentic Commerce 14:56
  32. Cursor's Gambit: Are "Always-On" AI Agents the End of Coding as We Know It? 18:58
  33. GitAgent: The "Docker for AI Agents" Trying to Unify a Fractured Ecosystem 16:55
  34. The Benchmark Battle: Has Cursor's Composer 2 Found the Sweet Spot? 12:33
  35. The Coinbase Playbook: How to Roll Out AI to 1,000 Engineers Without It Backfiring 19:54