• merge conflicts
  • Try speculative things to learn from working examples
  • agents-reframing
  • @withoutclass on Mastodon:

    I found it confusing that I was feeling more burnt out from using them than less, but I also realized I was context switching way more while waiting for the robot on top of having to articulate thoughts more to the robot as well.

  • Building understanding of large codebases via speculative prototypes and arguing with the agent