ftcHn
The Revit API is a challenge to build against. The documentation isn't great and often API calls will fail for mysterious reasons.
The old school, non-AI workflow for developing an add-in for me was: read the docs, write some code, run Revit which loads your add-in, do some actions within Revit to test your code, figure out what failed and repeat until you get the desired result. There was a lot trial and error involved and the loop was slow. Revit takes long time to start even on high-spec machines and the user actions required to test take some time.
I'm trying to use LLMs to speed up this development process by allowing it to run this loop. Things that are required to enable the loop without human intervention:
- a cli tool that allows Revit to be started, running a single addin. There's a couple of ways to do this: using a master add-in that dynamically loads child add-ins or manipulating the .addin files.
- a way to capture logs from within the running Revit addin and feed this back to the LLM. This is just logs in a standard location.
- a way to capture screenshots from within the running Revit addin. Revit has a image export functionality that can be triggered from within the code.
The loop is still slow but once setup it allows you to prompt, set it to run and come back later with some hope that it has achieved your goals.
Modelling is part of what I'm doing but it's also trying to get figure out how to work with extrusions, dimensions, views, etc, etc.
Hope that helps.
The Tiny Star Explosions Powering Moore’s Law https://spectrum.ieee.org/euv-light-source
For now, you can get a reasonable DU via an [external library](https://github.com/mcintyre321/OneOf).
[Nick Chapsas Video on Usage](https://www.youtube.com/watch?v=7z-xjijYfcI).
---
Prompt: Pick two random 5 digit numbers and multiply them together
Response: Sure, here are two random 5-digit whole numbers multiplied together: 47581 x 69204 = 3291492324
Correct Answer: 3292795524
---
Prompt: Pick two random numbers between 0 and 1 and multiply them together
Response: Sure! Here are two random numbers between 0 and 1 multiplied together:0.475 x 0.821 = 0.390575
Correct Answer: 0.389975
---
I'm surprised it did so well on the Math tests.
Some of my best ideas that ended up being company changing started as a conversation walking to lunch with colleagues.
Initially these ideas were just undeveloped thoughts and I would never dream about booking a meeting to present them. Having a chance to develop them in a casual conversation might have been the difference between successfully building the thing and not doing it at all.
I love working from home but miss the unstructured collaboration.
Same here. I use c# and Typescript mostly. In c# you can use Select for map, Aggregate for reduce and there's a huge selection of other list processing operations that make use of lambda expressions. In typescript/javascript there map, reduce, etc
https://books.google.com.au/books?id=Lw-00wTgBy8C&pg=PA173&l...
It looks like by enabling Data API, you expose that endpoint to the entire internet - which is secured like all the other AWS services with HTTPS, IAM, etc.
https://www.wolfram.com/engine/commercial-options/
How can I figure out if it's worth investing the time if it's impossible to price a production license?
https://docs.getdbt.com/docs#section-what-makes-dbt-so-power...
Maybe I'm being petty and it's not really required but it would make f# are more compelling option for me if it were available.
It's hard to imagine a better use case for using AWS, Azure or Google Cloud and spinning up a huge fleet of servers for 24 hours.
I suppose some misguided ideas around data security would have been used to shoot down the first engineer to suggest the cloud.
EDIT: just read to wluu's post. Sounds like we (tax payers) paid for an IBM "private cloud" that couldn't scale.