I have observed that the understanding of drawing quality by the General LLM models differs for CAD exported drawings vs Scanned drawings. CAD exported drawings capture models are able to capture the lines and curve objects. Were as Scanned PDFs it's just one image. Is there any other open source model which reads scanned PDFs better than the generic models like gemini or claude opus ? The constraint I see with any generic multi model LLMs os downsample to smaller size and model never sees the pixel.

This has been a big month for me. Last week I became a Dad (super excited but sleep deprived), also feels very wierd calling myself a Dad. So this month I'm in a tiny bit of a holding pattern but I've got two main focuses this month. 1. I want to engage way more on here and restructure the classroom. We've got sample projects, tons and tons of templates and more. I really want to try and get people to use them 2. Rebuild my email newsletter so its genuinely useful for people. I'm planning on breaking each week down into three parts: news updates - what's happened in the last week of construction/AI, inform - some interesting insight or perspective change and work - a new approach or solution to a task. What are your goals for October? Comment them down below!