zlacker

[return to "Gemini 3 Pro: the frontier of vision AI"]
1. knolli+9P[view] [source] 2025-12-05 19:58:32
>>xnx+(OP)
I do some electrical drafting work for construction and throw basic tasks at LLMs.

I gave it a shitty harness and it almost 1 shotted laying out outlets in a room based on a shitty pdf. I think if I gave it better control it could do a huge portion of my coworkers jobs very soon

◧◩
2. amorzo+wS[view] [source] 2025-12-05 20:16:33
>>knolli+9P
Can you give an example of the sort of harness you used for that? Would love to play around with it
◧◩◪
3. knolli+261[view] [source] 2025-12-05 21:25:03
>>amorzo+wS
I've been using pyrevit inside revit so I just threw a basic loop in there. There's already a building model and the coworkers are just placing and wiring outlets, switches, etc. The harness wasn't impressive enough to share (alos contains vibe coded UI since I didn't want to learn XAML stuff on a friday night). Nothing fancy; I'm not very skilled (I work in construction)

I gave it some custom methods it could call, including "get_available_families", "place family instance", "scan_geometry" (reads model walls into LLM by wall endpoint), and "get_view_scale".

The task is basically copy the building engineer's layout onto the architect model by placing my families. It requires reading the symbol list, and you give it a pdf that contains the room.

Notably, it even used a GFCI family when it noticed it was a bathroom (I had told it to check NEC code, implying outlet spacing).

◧◩◪◨
4. ftcHn+7y1[view] [source] 2025-12-06 00:30:21
>>knolli+261
I'm going to try to get it to generate extrusions in Revit based on images of floor plans. I've tried doing this in bunch of models without success so far.
[go to top]