main
John Lauer First AI PCB with Grok: clip 5, Grok runs Adom Fields (60 fps GPU playback) 327f0e0 5d ago
{
 "video": "/adom/grok-bridge/render/first-ai-pcb/clips/05-fields.mp4",
 "title": "Clip 5: Grok runs Adom Fields",
 "poster": "/adom/grok-bridge/render/first-ai-pcb/clips/05-fields.jpg",
 "chapters": [
  {
   "t": 0,
   "title": "Grok solves it"
  },
  {
   "t": 16.4,
   "title": "Played on a GPU"
  },
  {
   "t": 23.5,
   "title": "Current"
  },
  {
   "t": 34.3,
   "title": "Heat and temperature"
  },
  {
   "t": 39.4,
   "title": "EMC"
  },
  {
   "t": 45.9,
   "title": "Noise"
  },
  {
   "t": 52.6,
   "title": "Power delivery"
  },
  {
   "t": 55.0,
   "title": "The thermal vias"
  }
 ],
 "captions": "WEBVTT\n\n00:00:00.000 --> 00:00:02.300\nHow does Grok run Adom Fields?\n\n00:00:02.500 --> 00:00:03.600\nOn its own computer.\n\n00:00:03.800 --> 00:00:11.200\nIt installs Adom Fields from the wiki,\nsaves its board with the zones filled,\nwrites the spec from its own design, and\nsolves.\n\n00:00:11.450 --> 00:00:16.250\nIts browser shows the app, but with no GPU\nit draws three frames a second.\n\n00:00:16.450 --> 00:00:23.300\nSo Grok publishes its exact solve to a\nprivate wiki page, and we play it back on\nthe office PC's GPU.\n\n00:00:23.550 --> 00:00:30.800\nCurrent density peaks at 21 A/mm\u00b2, on the\n5 V output between the inductor and the\noutput caps.\n\n00:00:30.950 --> 00:00:34.100\nHere is the current flowing, with the\nlayers pulled apart.\n\n00:00:34.300 --> 00:00:39.250\nThen the heat, and U1's temperature: 12 \u00b0C\nabove ambient in still air.\n\n00:00:39.450 --> 00:00:45.700\nEMC: the switching loop sits 48 dB under\nthe FCC Part 15 class B limit.\n\n00:00:45.900 --> 00:00:52.400\nNoise: the switch node puts 45 mV on the\nenable pin, close to its 50 mV budget.\n\n00:00:52.600 --> 00:00:54.900\nPower delivery: both rails pass.\n\n00:00:55.100 --> 00:01:00.840\nAnd the one medium issue: Grok's four\nthermal vias sit just outside the zone\naround U1.\n"
}