If your problems stem from Microsoft's invasive updates and policies, I'd suggest switching to Windows 10 IoT Ltsc Enterprise, https://massgrave.dev/. It's a version meant for stable systems like your ATM machines, which means minimal AI bloat pushed to you. Startup is really fast too.

Spread it around. MS needs it's head screwed right.

you got any recommendations for local models setups? lightweight enough for a 5060 if possible

Yes I do! 5060 is tough because you have 8GB of VRAM. That means any model you load onto it will have to be smaller than that (a model that is 6GB on hugging face will take up 6 GB of VRAM just loaded onto your GPU, then need some more headroom for the actual inference).

So, you could get away with Qwen3.8 quantized to 1 bit which is available here: https://huggingface.co/unsloth/Qwen3.8-27B-GGUF.

Now, depending on how much RAM you have, you can offload some of the inference to the RAM, but this is a performance bottle neck (less tokens per second)

I haven't tried the 1 bit quantization yet, but I often run the Q4 quantization on a 3090 machine I have Qwen3.8-27B-UD-Q4_K_XL.gguf which is 17.6GB and fits nicely on a 3090 with 24GB of VRAM.

To run these models you need to download them (usually from hugging face) and run them with something like llama.cpp (I personally recommend this over ollama). If you are doing that you need a GGUF file which is available from many people on hugging face, most famously the account named "unsloth" which takes the Safetensors weights that a company publishes and turns it into these GGUF files which can be run on a desktop with llama.cpp.

With the 5060 you are limited. If you can get a 3090 you can do really great local work with Q4 Qwen3.8-27B

In my personal set up (which I will release fully open source soon), my qwen model can actually browse the internet as if it was me (you can actually watch it view pages, its pretty cool), which means your little local model can scrape up to date info off the internet.

Hopefully that was helpful. Open source is the future!

The quote "vastness of an ocean with the depth of a puddle" describes what the AAA-hollywood games complex aspire to be.

One theory is that building/maintaining games is knowledge work, and each worker you retain helps with that. But as always, human social groups can deviate against the common good, but they can also boost it, and in this case even protect against abuses of the masses workers by management.

I'd think you overrate christianity too much. Javanese culture is known to be very welcoming of other traditions.

I'm a little more interested how they automated the process to such a degree. How do they do it? Subagents?

After about three weeks I hand drove three agents in parallel for 8-10 hours/day. There is very little automation.

Damn. Props to them, looks great. Always experienced 40k through books and games, there's so much difference when it's a universe.

Disagree. School exams test for academia-readiness too. And sometimes the schools and lecturers are filled with ideology irrelevant to real work.

Career exams tend to be a mix but a lot less ideology.

isn't the process per connection restriction pretty heavyweight though?

Psychologists have been saying for ages that a good job interview is a small version of what the job requires them to do. But as always with most professions with people (and hence ego) involved, these people either mimic what the trending company in their sector does or test irrelevant academia knowledge.

Maybe for such changes to happen the whole profession to go down a notch in prestige. Not sure if people can stomach that.