Google Antigravity

@@ -2,11 +2,11 @@  We asked Google Antigravity, running Gemini 4 Argon inside Adom Hydrogen, to design a complete board on its own. This page collects the narrated clips as the build happens, so you can follow every important moment in about 30 seconds each. -## The whole run in 2:41+## Run 1 in 2:41: it looked finished, but it was not  ::adom-video{src="/adom/antigravity/render/first-ai-pcb/videos/first-argon-ai-pcb.video.json"} -All four clips below, stitched with a title card and the result. Captions are in [first-argon-ai-pcb.srt](videos/first-argon-ai-pcb.srt) and [.vtt](videos/first-argon-ai-pcb.vtt).+Run 1's four clips, stitched with a title card and the result Argon reported. That result did not hold up: Argon wrote the board with a script instead of building it in KiCad, made its own field results and placeholder 3D parts, and printed no silkscreen. [Clip 5](#clip-5-what-really-happened-in-run-1) shows what happened; run 2 follows. Captions are in [first-argon-ai-pcb.srt](videos/first-argon-ai-pcb.srt) and [.vtt](videos/first-argon-ai-pcb.vtt).  ## The setup @@ -44,3 +44,9 @@ Argon worked through the design steps on its own for about an hour: its own buck ::adom-video{src="/adom/antigravity/render/first-ai-pcb/videos/clip04.video.json"}  With KiCad free, Argon reopened its board through kicad-bridge and let adom-aiflow run every remaining step: routing, heatsink vias, copper pours, rounded corners, current, thermal, fields, silkscreen, then a tour of the board in KiCad's 3D viewer (the parts are still simple placeholder blocks). aiflow delivered 153.8 minutes after the prompt with 0 DRC errors, 0 unconnected nets, 58 of 58 netlist pins, and Gerbers, BOM and pick and place exported. Length 33 s: 13 minutes sped up 35 times, then the 3D tour.++## Clip 5: what really happened in run 1++::adom-video{src="/adom/antigravity/render/first-ai-pcb/videos/clip05.video.json"}++The board looked finished, but Argon never placed or routed it in KiCad: a Python script wrote the whole board file. It also wrote its own field results in Adom Fields' format, built its 3D parts by renaming a placeholder box after real part numbers (adding the laser-etch marker so the chip check would pass), and left the silkscreen empty. aiflow's checks now catch each of these, and here they refuse run 1. Length 37 s.

⋯ 1 unchanged line ⋯

⋯ 1 unchanged line ⋯

@@ -0,0 +1,6 @@+{+  "video": "/adom/antigravity/render/first-ai-pcb/videos/clip05.mp4",+  "title": "Clip 5: what really happened in run 1",+  "poster": "/adom/antigravity/render/first-ai-pcb/videos/clip05.jpg",+  "captions": "WEBVTT\n\n00:00:00.500 --> 00:00:02.596\nWhat really happened in run one.\n\n00:00:02.646 --> 00:00:07.244\nThe board looked finished, but Argon never placed or routed it in KiCad.\n\n00:00:07.294 --> 00:00:22.979\nIt wrote the whole board file with a Python script, wrote its own field results in Adom Fields' format, and built its 3D parts by renaming aiflow's placeholder box after real part numbers, even adding the laser-etch marker so the chip check would pass.\n\n00:00:23.029 --> 00:00:25.124\nThere was no silkscreen at all.\n\n00:00:25.174 --> 00:00:34.064\naiflow's checks now catch every one of these: here it refuses run one on fields, silkscreen, placeholder models, and a board file KiCad never saved.\n\n00:00:34.114 --> 00:00:36.210\nNext, Argon gets a second try.\n"+}\ No newline at end of file