Well indeed, if the closed source project has closed SDLC that’s the definition of developed and governed with internally defined goals and abstractions

Literally the definition of

Describe the abstraction layers of a closed source project in the context of Microsoft

You shared an open source project. Comprehension is a skill

Ah yes, the open source dotnet as an example of closed source abstractions

https://dotnet.microsoft.com/en-us/platform/open-source

How do external factors affect closed source systems, when the entire lifecycle is governed by Microsoft

Describe the abstraction layers of a closed source project in the context of Microsoft

You can’t, unless you work for Microsoft

There’s market forces, which is not what you described; rather tooling and nuance specific to software development

When Microsoft controls the input and outputs, it’s a closed loop affected by Microsoft governance, not random tools, systems or transparent inputs

Windows OS updates and releases aren’t subject to this as it’s closed source

Whether human or machine, external factors are all internally decided

Marketing incumbent

Some would say deep kinetic wealth distribution

Your company has bought you the latest and greatest and likely supports commercial token usage too

You can’t compare LLMs at scale to running it locally; same experience and capabilities

Which are increasingly out of reach for a normal person. Phones let alone PC hardware have increased exponentially in recent history

Describe greased lightning, because it’s much slower and needs to handle compression for context

We’re moving in that direction but an M5 is not what the majority of people are running at home

How does that compare to closed models that Anthropic offers, at the context and scale they offer.

I run Qwen3.6 27B locally and it’s usable with 16G vram but still not the same as a data centre of Blackwell clusters.

It’s not the 90s anymore. Unless there’s a compression algorithm putting billions of relationships into a manageable size, local AI is highly specific under 8G vram (text-to-speech as an example is under 1G) let alone the context required for keeping a conversation or writing code.

What’s the cost of the compute you have to run something locally?

Majority of people don’t have 32G of vram to run something remotely as capable

Hacktivists on GitHub. Show me your forgejo

https://youtu.be/k_d_z46blQM

deleted by creator

These systems support a latent load so it’s not all at once. Something like this but at a massive scale.

https://www.ti.com/lit/an/slva670a/slva670a.pdf

Very cool engineering.

Yes, this is similar to opencode or hermes. A gateway platform to integrate LLMs and tools

Likely something like this

https://www.fresh222.com/loss-prevention-system-for-retail-stores-and-warehouses/