your point about gas pockets making the shield blow out made me curious

I found this visual schematic of the spalling helpful - https://vectree.io/c/the-physics-of-ablative-spalling-in-ori...

It finally makes sense why the gas needs to leak out... if it gets trapped behind the burnt outer crust, the pressure just blows pieces of the shield off like a tiny bomb

the list is funny :)

So it counts how many times I was angry?

is it that bad? maybe that is a secret for a long life. I want a job that never disappears :)

exactly, makes me think... if person who makes the bread does not feed his own family, something is wrong

I did not know, that NVFP4 was handled at the silicon level... until I dug deeper here - https://vectree.io/c/llm-quantization-from-weights-to-bits-g...

I still don't think I understand it. I saw those nvfp4 models up by chance yesterday and tried them on my Linux PC with a 5060TI 16gb. Ollama refused to pull them saying they were macOS only.

I assumed it was a meta-data bug and posted an issue, but apparently nvfp4 doesn't necessarily mean nvidia-fp4.

https://github.com/ollama/ollama/issues/15149

They are nvidia-fp4 weights, but CUDA support isn't _quite_ ready yet, but we've got that cooking.

Agreed, Spring Framework is quite simple... just look here - https://vectree.io/c/spring-framework

BTW magpies have passed the mirror test

valid point, it reminds me of video games. GPUs got faster, devs pushed higher resolutions, more complex lighting instead of saving power :)

spot on... that difference between evaluation and storage is exactly why C++ is so hard to keep in my head

I thought constexpr was a hard physical constant, but in reality it's a weird hybrid

this visualisation helped me to wrap my head around it - https://vectree.io/c/c-constness-and-evaluation-qualifiers

100% agree