• Software Factories And The Agentic Moment: One company decides to run an experiment where humans don’t write any code. They can only prompt agents or set agents up to prompt eachother.
    • Patterns they identified
      • “Digital twin universe” in which they clone software they use to better simulate
      • “Gene transfusion” where ideas in one project are copied into another
      • “Shift work” where you try to move a task that needs a human into an agent loop somehow
    • And the harness that makes it possible (allegedly): Seed -> Validation harness feedback (closed loop system). You should always start with a seed which can be a spec or high level description of the goal which you use to create a spec or an existing code base you can build up context with in an agent.
  • NASA’s Perseverance Rover Completes First AI-Planned Drive on Mars: Generative ai looks at an image, identifies obstacles and routes around them.
  • NASA’s Perseverance Now Autonomously Pinpoints Its Location on Mars: Nasa rover can figure out where it is by looking at pictures and a topological map built by satelites. Prior to this it had to wait for an update from earth if it wasn’t sure where it was. It’s safest for a rover to stop rather than keep going when it’s not sure about its surroundings. Round trip time for a message from earth is on the order of minutes so very slow.