Dave " " Buchhofer

Developer, 3D Artist, 'Ex'-ArchViz. Software Dev @ Matterport - Current obsession: 3Dux, locomotion, MTB. (he/him)

[Unemployed Capital Allocator @atelicinvest]

The funniest thing about LLMs is that they let you generate endless work in domains where you’re completely unqualified to evaluate the output.

[Dave " " Buchhofer @vsaitoo]

@lucasmeijer you could always @ the particular skill.md file you want to reference from anywhere in a prompt

[Dave " " Buchhofer @vsaitoo]

@badlogicgames we gave up enough training data for now eh?

[tender @tenderizzation]

gpt 5.5 has goblins and can think. claude 4.7 doesn’t have goblins and can think. so it’s not the goblins that make the models think, it’s something else entirely

[Dave " " Buchhofer @vsaitoo]

@micheltamanda @LottoLabs i put it under the base with the ollama key as the version for lack of a better way atm

[Dave " " Buchhofer @vsaitoo]

@lucasmeijer alas the compressed sand doesn’t comprehend very well yet

[Dave " " Buchhofer @vsaitoo]

@RhysSullivan @kenwheeler that and very few are including any context of what they're actually working on. Lot's of stuff works fine for my homegrown bullshit 3d splat pipeline 'work', BUT that's a whole different ballgame from the 3d/engine/ux real work that a bajillion customers rely on heh.

[Dave " " Buchhofer @vsaitoo]

@DavidKPiano sweet thanks, I was just trying out xstate last week and this seems to have made some solid suggestions on where to push next to improve my machine.

[Dave " " Buchhofer @vsaitoo]

@dmarcos @__tinygrad__ A lot of that researchy/mesh gen stuff is very heavily tied to cuda, and isn’t always a one-to-one port to get working

[Dave " " Buchhofer @vsaitoo]

@dmarcos @__tinygrad__ I initially started playing with it with the intent to do splats. I have a local pipeline that is a mixture of brush and tinygrad that kind of works, but it's been a learning experience. Nothing‘s going to be out of the box yet. It's not a general driver, it's a backend for TG

[Steve Ruiz @steveruizok]

me, scoffing in the back row of SIGGRAPH: ok I guess this is good if I ever need to render a teapot I guess??

[Dave " " Buchhofer @vsaitoo]

@tosolini @XGRIDS_OFFICIAL @XRarchitect Always a classic effect

[Dave " " Buchhofer @vsaitoo]

@keenanisalive Thanks, looks like a handy replacement/enhancement on the 'gltf-transform inspect' and https//gltf.report drag-and-drop options I tend to fall into currently depending on which use case I'm in at any moment.

[Dave " " Buchhofer @vsaitoo]

@RadianceFields @lichtfeldstudio @SplatK1ng Fancy giveaway SplatKing / @SplatK1ng and quality engagement hackery sir, /salute. Will check it out.

[Dave " " Buchhofer @vsaitoo]

@__tinygrad__ Yep, set up a 3090 on my desk a couple weekends back, it's been an interesting experiment

[Mario Zechner @badlogicgames]

your biggest enemy is still complexity. it's also your agent's biggest enemy. but it has no holistic view of your code base, so it keeps adding complexity.

and you think that's how it's supposed to be, because the clanker shat it out, and you don't know the stack.

glhf!

[dax @thdxr]

when you think of feature A your job is to recognize that it's actually a special case of feature X and if you implement feature X it unlocks feature A B C

people are struggling with this lately because they can't think bigger than what their agent can do

[Dave " " Buchhofer @vsaitoo]

neat, 38tok/s is better than I expected.

Especially given I'm not sure how many terrible sins have been generated while getting it to this point.

[Dave " " Buchhofer @vsaitoo]

It's dangerous now that it’s easy-ish to run a wild ass experiment just to learn?
can I run the new qwen model on osx locally via my old 3090 in tinygrad vulkan -> llama.cpp -> egpu

osx egpu worked, it's ~3x faster than the same on metal for stuff that can stay GPU resident?

[Dave " " Buchhofer @vsaitoo]

Unsurprisingly, it's choking under the sheer weight of the vibes before it's functional, but I still enjoy this learning by osmosis/fail style on occasion.

Back to things I KNOW how to do for a while, see where this ends up next weekend maybe!

[Dave " " Buchhofer @vsaitoo]

it loaded! 🎉

✅ Qwen3.5-35B-A3B loaded successfully!
Architecture: qwen35moe
Blocks: 40
GatedDeltaNet: 30, Transformer: 10
Experts: 256 total, 8 active

That's realize=False though — and a whole lot of random ass changes. Guess we'll try more tomorrow after all?