E.g just now I ran:

~~~

What's the inverse of this matrix?

[[0.0759688880587972, 0.3299493758880664, 0.14599823333009276, 0.09897577338235164], [0.7478951343477207, 0.9006422280032432, 0.3137352150172843, 0.5974301357799204], [0.5568700534103693, 0.648666832906366, 0.5280912469659284, 0.5753861797637815], [0.7905984807343551, 0.053757547259005944, 0.9632727273522135, 0.44727851917969785]]

~~~

Reasoning output:

~~~

The user is asking for the inverse of a matrix. Since they want the result, I will compute it and present it as a matrix in Markdown. I’ll use Python for the calculation but won’t include any code in the final answer. It’s best to show the resulting matrix in Markdown so the user sees only the output, as requested. I’ll use Python to compute it and then provide the result without extra code.

import sympy as sp import numpy as np

# define the matrix M = np.array([ [0.0759688880587972, 0.3299493758880664, 0.14599823333009276, 0.09897577338235164], [0.7478951343477207, 0.9006422280032432, 0.3137352150172843, 0.5974301357799204], [0.5568700534103693, 0.648666832906366, 0.5280912469659284, 0.5753861797637815], [0.7905984807343551, 0.053757547259005944, 0.9632727273522135, 0.44727851917969785] ], dtype=float)

# calculate inverse invM = np.linalg.inv(M)

invM

~~~

And then I get a nicely formatted latex matrix as the final outcome.

(edit: that's 04-mini-high)

Founded 6 February 2013; 11 years ago

https://en.wikipedia.org/wiki/Alternative_for_Germany

[Granted, many of the current political parties in Germany are from '45 so also not that old, but one of the oldest parties is a strange claim]

And with multimodal LLMs there is also some ability for multiple sensory inputs.

An open-source toolkit for developing digital platforms in the built environment. With IfcOpenShell, you can read, write, and modify Building Information Models (BIM) using the IFC standard — a versatile and open digital language spanning the entire lifecycle of buildings, from design to construction and beyond.

Now including Bonsai, a Blender-based 3D editor to create and edit multidisciplinary information within IFC models.

The built environment is a major contributor to emissions, making sustainability in design, construction, and operations an area we can work on with data-driven decisions unlocked by open source tools.

CAD/BIM has long faced lock-in by the proprietary nature of traditional tools. We aim to change that.

C++ / Python / 3D / Computational geometry / CAD / BIM

In BIM, a building (or any construction work really, bridges/tunnels/...) is described as a set of components with explicit information (the I), for example: this is a wall with fire rating XYZ. The geometry/representation is only one aspect of that wall. This information is exchanged using actual data models (the M) - hopefully using IFC (another acronym, less meaningful this time), which is the open and vendor neutral standard to encode such building models.

There's a lot of disciplines (architects, structural engineers, heating and ventilation, city planners and municipalities, planners, builders, owners, tenants). Also, building have a long lifetime, that extends way beyond the typical maintenance period of proprietary software. And the sector has a massive impact on our well being as well as environmental goals.

Encoding this information in a semantic and computer-interpretable has enabled better ways of working together, but there's still much potential and many interesting challenges (come join us!) ahead of us to make a better built environment a reality!

Indeed, a fair amount of people believe that the IFC is intentionally unnecessarily complex to limit interoperability and retain a monopoly.

Over time, I've come to believe hanlon's razor is also in play here and it's more of a poor understanding of use cases, academic ideas blowing up scope and inheriting obscure schema and serialization tech.

Meshes + metadata can facilitate most of the use cases in industry today, which is coordination, interference checks and visualization.

But at the same time, there's some pretty compelling use of the standard that requires slightly more semantic geometry descriptions:

- calculating geometric quantities according to local norms, which requires some additional geometric knowledge on things like openings and the axis of a wall for example

- The opening direction of doors is often good to know, but this is just a convention on the local transformation matrix, so could be just meshes.

- steel manufacturing can derive quite a bit of information from the IFC geometry, like parametric cross section profiles and where to drill for bolt holes and using which diameter

And then there is the ultimate end goal according to some to be able to exchange all parametric and constraint information from the native model. But this is still quite far out.

The challenge for future editions of the spec is to better align required complexity of certain use cases with a more modular spec so that you depend on a more appropriate amount of complexity.

Btw. since you mention Blender. The BlenderBIM addon https://blenderbim.org/ is actually one of the most avid users of complex and parametric constructs in IFC :)

We're quite close now to delivering the final version of IFC4.3: the open standard for BIM (building information modelling), now including semantic modelling of long linear infra https://ifc43-docs.standards.buildingsmart.org/ Eagerly awaiting to replace your PDF.

We're hiring for validate.buildingsmart.org

In the construction sector we've long communicated using drawings primarily. A recent trend is to communicate using semantic information models (Building Information Modelling). We're a vibrant open community (e.g https://github.com/IfcOpenShell/IfcOpenShell/)

Data integrity, validation and trust are key concerns when exchanging such models. Under the umbrella of the main standardization organization in this field, we have been building validate.buildingsmart.org based on open source software for some time now. We've built quite a successful prototype to demonstrate feasibility and gather a first audience.

Now, we're looking to further develop the web platform and scale up for some exciting new features such as software application metrics and certification.

We're looking for a seasoned freelance/part-time dev. Affinity with AEC is not a prerequisite, but familiarity with some of the following things is: Django, cloud native, feature flagging platforms, Azure (databases, cli, auth, ...), Selenium or similar, k8s/terraform/portainer.

Get in touch via tk /a/ aecgeeks _ com

While consciousness is maybe more elusive in how it functions in a brain, it's a biological trait that makes not so much sense to compare to a LLM which simply regurgitates fragments from text produced by conscious humans. So I don't see an immediate conflict.

It would be interesting to include things like OpenWorm (and later OpenFish, OpenCat, OpenHuman) in the discussion, but decoupled from the biological mechanisms I find it hard to develop a stance on that.

It's potentially important as there aren't that many projects from the 80s in the list, so maybe has an impact on the trend line.

(a trend line that would look similar if you look at time between proprietary alternatives I guess... a fact of the increasing amount of time spent on software engineering?)

I read a lot of comments on the intrinsic difficulty of earning money with foss, so advising against it or to treat it as a secondary side project. It's pragmatic, sure, but sometimes foss is a central to the value proposition, like in situations that require high amounts of trust or adaptability. A couple of hours a week is not always sufficient to retain momentum. So imho there is really a need for true foss business models.

Also keep in mind people of all ages are allowed to ride bikes, which is luckily not the case for cars. This source does say elderly and children are more likely to be part of cycling accidents (not necessarily fatal) https://www.veiligheid.nl/kennisaanbod/infographic/infograph...

Also driving under influence is (hopefully) much more prevalent in case of cyclists.

Hence, car drivers switching their transportation mode to bikes don't have the same risks as the entire cycling population.

Blender's user interface is fully scriptable in Python, which means you can really adapt to your personal workflows or that of the company

BlenderBIM accomplished a lot in about a year, but I guess we're all aware of what kind of monumental undertaking this is.

(I work on a related library)

That said, if you need to mix various modules on conda it can really be a challenge to find a conflict-free configuration, I agree.