{
  "type": "miscellanea",
  "draft": false,
  "title": "Miscellanea for 2025-06-18",
  "time": "23:59:00-07:00",
  "slug": "miscellanea",
  "tags": [
    "miscellanea"
  ],
  "attachments": [],
  "year": "2025",
  "month": "06",
  "day": "18",
  "isDir": false,
  "date": "2025-06-19T06:59:00.000Z",
  "postName": "2025-06-18",
  "html": "<ul>\n<li>Hello world!</li>\n<li>Since I'm bouncing between multiple teams' projects, this LLM agent-assisted coding thing reminds me of <a href=\"https://wiki.eveuniversity.org/Mining#Dual_account_mining\">multi-box mining in EVE Online</a>.<ul>\n<li>I haven't done that in years, but it was a way to make mining more interesting. You could fill in the lulls in gameplay by swapping between ships, treating it more like real-time strategy.</li>\n<li>Apparently, <a href=\"https://www.youtube.com/shorts/ijoXyVTv83Q\">EVE Online multi-boxing UI has gotten more sophisticated these days</a>? I can only imagine this is the direction coding agent orchestration will head.</li>\n<li>It's totally <a href=\"https://en.wikipedia.org/wiki/Plate_spinning\">spinning plates</a> and it's a more energy-consuming activity than I might have first expected.</li>\n<li>I'm really leaning on the Command-Backtick button to cycle through IDE windows to shepherd the Claude Code sessions as they crunch through execution plans.</li>\n<li>There is kind of a hyperfocus flow state available—not in the coding on individual projects, but in swapping between agents, keeping things running with answers to questions, performing rescues from ditches.</li>\n<li>This seems appealing to my ADHD brain, until or unless I get distracted in a way that lets plates start falling.</li>\n<li>I am finding that writing or generating gratuitous notes as context for both me and the LLM is really handy. Especially helps me remember what I was trying to accomplish when I last cycled into some particular IDE window.</li>\n</ul>\n</li>\n</ul>\n",
  "body": "\n- Hello world!\n- Since I'm bouncing between multiple teams' projects, this LLM agent-assisted coding thing reminds me of [multi-box mining in EVE Online](https://wiki.eveuniversity.org/Mining#Dual_account_mining).\n\t- I haven't done that in years, but it was a way to make mining more interesting. You could fill in the lulls in gameplay by swapping between ships, treating it more like real-time strategy.\n\t- Apparently, [EVE Online multi-boxing UI has gotten more sophisticated these days](https://www.youtube.com/shorts/ijoXyVTv83Q)? I can only imagine this is the direction coding agent orchestration will head.\n\t- It's totally [spinning plates](https://en.wikipedia.org/wiki/Plate_spinning) and it's a more energy-consuming activity than I might have first expected.\n\t- I'm really leaning on the Command-Backtick button to cycle through IDE windows to shepherd the Claude Code sessions as they crunch through execution plans.\n\t- There is kind of a hyperfocus flow state available—not in the coding on individual projects, but in swapping between agents, keeping things running with answers to questions, performing rescues from ditches.\n\t- This seems appealing to my ADHD brain, until or unless I get distracted in a way that lets plates start falling.\n\t- I am finding that writing or generating gratuitous notes as context for both me and the LLM is really handy. Especially helps me remember what I was trying to accomplish when I last cycled into some particular IDE window.",
  "parentPath": "./content/posts/2025",
  "path": "2025/06/18/miscellanea",
  "needsBuild": true,
  "prevPostPath": "2025/06/18/ai-anger-way-forward",
  "prevPostTitle": "On AI, anger, and the way from here",
  "nextPostPath": "2025/06/30/miscellanea",
  "nextPostTitle": "Miscellanea for 2025-06-30"
}