Grok Bot

{
 "video": "/adom/grok-bridge/render/first-ai-pcb/clips/06-molecule.mp4",
 "title": "Clip 6: Grok's first molecule",
 "poster": "/adom/grok-bridge/render/first-ai-pcb/clips/06-molecule.jpg",
 "chapters": [
  {
   "t": 0,
   "title": "The molecule standard"
  },
  {
   "t": 14.6,
   "title": "The J4 neck"
  },
  {
   "t": 30.8,
   "title": "Current and heat"
  },
  {
   "t": 39.0,
   "title": "EMC and power"
  },
  {
   "t": 46.3,
   "title": "Grok's first molecule"
  }
 ],
 "captions": "WEBVTT\n\n00:00:00.000 --> 00:00:03.400\nOne correction: Adom boards follow the\nmolecule standard.\n\n00:00:03.610 --> 00:00:12.200\nSo Grok reworked its board on its own\ncomputer: machine pins in all four\ncorners, machine contacts on the edges\ninstead of screw terminals, everything on\na 2 mm grid, and a 36 by 20 mm outline\nwith rounded corners.\n\n00:00:12.440 --> 00:00:14.400\nGrok added an enable contact so the\ncontrol panel can switch it off.\n\n00:00:14.600 --> 00:00:22.700\nAdom Fields found a real neck where the 5\nV output entered its contact: 85 A/mm\u00b2 on\na thin ring.\n\n00:00:22.890 --> 00:00:30.600\nGrok widened the copper and added vias,\nand it dropped to 9.\n\n00:00:30.770 --> 00:00:34.550\nHere is the current flowing through the\nnew copper.\n\n00:00:34.740 --> 00:00:39.000\nWith half the copper area, U1 now rises 24\n\u00b0C, still under its 40 \u00b0C budget.\n\n00:00:39.030 --> 00:00:46.100\nEMC margin holds at 48 dB, and both rails\npass.\n\n00:00:46.280 --> 00:00:47.800\nFour low issues remain.\n\n00:00:47.980 --> 00:00:51.050\nGrok's first molecule.\n"
}