"an AI “plan checker”" do you have some public benchmark for how many issues you can find?

how does this work behind the scenes?

Great questions. We’re working on a more formal public benchmark and will share results as our dataset grows. Today, we typically catch coordination issues like conflicting dimensions, missing callouts, building code and clearance violations that humans often miss in large sheet sets. Behind the scenes it’s a multimodal workflow: OCR + geometry parsing + cross-sheet callout graph + constraint checks vs. code/spec requirements.

is this only on the frontpage because this is an HN company?

how can you prove it works and doesnt hallucinate? do you have any actual users that have installed it and found it useful?

i would say theres engineers arent set up close enough to customer issues; theres too many layers in between

This is «politics» in terms of game theory, it is «news» in terms of occasion, and can claim some right to be here for its share of intellectual interest in the dynamics involved.

you know what would be a more interesting discussion? how russia and iran are using any army of bots and people behind the screen to sway public opinion; our actual democracy has been errroding for years and noone wants to talk about it.

> and noone wants to talk about it

Except we actually «talk about it» very frequently: we are well aware of the presence of informational warfare also after the articles so frequently published about it.

Why shouldn't it be? Learning about unusual and sometimes grim things that are outside of our bubble is a good thing.

agreed, he has a great piece on japans system