An update toward AI systems being able to reliably book flights this year (even if required to use legacy UIs). (Previous discussion: https://t.co/SCdLA9o00T) https://t.co/axJ2CL9HME
— Steve Newman (@snewmanpv) Mar 6, 2026
Under Secretary of War for Research and Engineering Emil Michael on being the CTO of the Department of War, applying lessons from Silicon Valley at the Pentagon, and his "holy cow" moment with AI vendors. 00:00 Silicon Valley to DC 02:03 Why the DoW cannot operate at "peacetime https://t.co/8BnP5yrdzI
— a16z (@a16z) Mar 6, 2026
Awesome job by the @databricks team My summary: They trained a model called KARL that beats Claude 4.6 and GPT 5.2 on enterprise knowledge tasks (searching docs, cross-referencing info, answering questions over internal data), at ~33% lower cost and ~47% lower latency. The key https://t.co/EWwiuverUX
— Jamin Ball (@jaminball) Mar 6, 2026
Boris Cherny (Head of Claude Code, Anthropic) just dropped ~90 mins on Lenny's Podcast about what happens after coding is solved. Just the clearest thinking I've heard on where software is actually going. My notes: 𝟭. 𝗖𝗼𝗱𝗶𝗻𝗴 𝗶𝘀 𝗹𝗮𝗿𝗴𝗲𝗹𝘆 𝘀𝗼𝗹𝘃𝗲𝗱. Boris has https://t.co/pw5om66Kex
— Anish Moonka (@AnishA_Moonka) Mar 6, 2026
Google just dropped another banger 🤯 They open-sourced the Agent Development Kit, and it perfectly pairs with Gemini 3.1 Flash-Lite. Means you can now build always-on AI Agents that run 24/7 at a negligible cost. 100% Open Source. https://t.co/1yUISHFkZz
— Simplifying AI (@simplifyinAI) Mar 6, 2026
I took my normal "exit plan mode" skill and expanded it into a "mega exit plan mode" skill that I find can be quite useful when you are trying to expand scope and/or just want Claude Code to delight you with new ideas. It's sort of like the expansive CEO to the normal skill's
— Garry Tan (@garrytan) Mar 6, 2026
Don't overload your AGENTS dot md files. Keep them brief. GitHub's analysis of 2,500+ repos found what makes AGENTS dot md files work: - provide the agent a specific job or persona - exact commands to run - well-defined boundaries to follow - clear examples of good outputs https://t.co/GFSEjLsx8C
— elvis (@omarsar0) Mar 5, 2026
