Literate Programming Resurges as AI Agents Solve 40-Year Problem
Literate programming—Donald Knuth’s 40-year-old paradigm for writing code as prose with embedded logic—is trending on Hacker News today with 221 points and 135 ...
Agent Safehouse: Sandbox macOS AI Agents at Kernel Level
Agent Safehouse uses macOS Seatbelt for kernel-level AI agent sandboxing. Install in 3 commands to ...
AI Brain Fry: Harvard Study Reveals Dark Reality
Harvard Business Review published groundbreaking research this week revealing “AI brain fry” – a new ...
Netflix Acquires Ben Affleck’s AI Filmmaking Startup
Netflix acquired InterPositive on March 5, 2026—Ben Affleck’s secretive AI filmmaking startup founded in 2022—with ...
Cursor Automations: Always-On AI Coding Agents End Prompt Loop
On March 5, 2026, Cursor launched “Automations,” ending the exhausting prompt-and-monitor loop that defines current ...
AutoResearch: AI Agents Run 100 ML Experiments Overnight
Karpathy's autoresearch lets AI agents run 100 ML experiments overnight on a single GPU. Tutorial covers setup, costs ($50-200), and avoiding validation overfitting. ...
AGENTS.md Files Backfire: ETH Study Shows 3% Drop, 20% Cost
ETH Zurich researchers just proved what many developers suspected: AGENTS.md context files don’t work the ...
Big Tech Pledges AI Power—But Who Really Pays the Bill?
Seven tech giants promised March 4 to fund AI data center power, but the pledge ...
AI Productivity Paradox: 92% Use AI, Gain Just 10%
92% of developers use AI coding tools, yet productivity gains stuck at 10%. Discover why ...
Ki Editor: AST-Based Code Editing Goes Structural Now
Code editors operated on text for 50 years. Ki edits AST nodes directly—delete a function, ...