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

Philadelphia, PA
Joined December 2008
Dave " " Buchhofer retweeted
If you remember this, your back probably hurts.
262
163
112
2,526
121,718
Dave " " Buchhofer retweeted
I can’t stress enough how little an idea matters compared to the agency of the people executing the idea. I have had the privilege of knowing and sometimes even working with some of the most successful people (by various metrics). The difference between mediocre and excellent work and outcomes is predominantly one of agency. In practice this means: they dont wait for things to happen to them they go out and make things happen for them. They don’t wait for someone else to do something, for someone to teach them, for someone to give them the path, etc. They just go out and find a way to do it. I think the single biggest superpower these people have is the realization/belief that the world around them is completely mutable. Most everything that happens is because a person made it happen. I used to tell people to look around the room you’re sitting in. Look at everything. Every noun. It almost all exists because a person willed it into existence. Nothing is stopping you from doing the same. I see people online all the time dismissing someone else’s success because “I had that idea first” or whatever. I mean… yeah? If so then the difference is… you. So a bit of a self own whenever I hear that. Number one tip: act with agency.
229
1,281
201
11,855
689,933
Dave " " Buchhofer retweeted
In my day we didn't need "/grill-me", we would hire a 24 year old designer, loosely describe the feature, ask them to imagine the user interface and draw it for us, then come to a shared understanding by roasting the shit out of the designs in an hours long humiliation ritual
18
14
4
441
22,385
The funniest thing about LLMs is that they let you generate endless work in domains where you’re completely unqualified to evaluate the output.
45
103
15
1,486
39,902
Dave " " Buchhofer retweeted
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
36
112
14
3,114
60,870
Dave " " Buchhofer retweeted
me, scoffing in the back row of SIGGRAPH: ok I guess this is good if I ever need to render a teapot I guess??
4
19
1
239
15,036
Dave " " Buchhofer retweeted
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!
25
37
3
406
47,753
Dave " " Buchhofer retweeted
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
65
56
15
1,115
44,293
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?
14
1
56
15,743
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.
47
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?
1
2
129
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!
1
54
Anyway, no one should take anything from this as fact. Seems obviously something that I'm just a little too early on, and I'm looking forward to where it goes when my comma has these new compute powers (!)
65
just half pushing on it until it explodes while walking the dog is a wild place to be?!
60
The VRAM problem seems architectural in tinygrad’s load path? need a Q4_0Linear that stores quantized blocks and dequants in the forward pass (like Int8Linear already does)?
52
The actual quantized files have mixed quant types all over. Had a script that requantized 60 tensors (Q5_0 -> Q4_0) In bartowski Q4_0. After that Pass 1 (realize=True): KeyError: ‘qwen35moe.feed_forward_length’ • Pass 2 (realize=False): MemoryError at ~18.71 GB allocation
59
Dave " " Buchhofer retweeted
New ad by the Norwegian Consumer Council: "A Day in the Life of an Ensh*ttificator"
211
3,072
412
17,219
2,375,646
> Status: GREEN. The eGPU stack works for LLMs on macOS. that’s a little bit of a stretch at one token per second for the 30 B model, but I wasn’t really expecting you to work at all. I just wanted to know where it broke. 3090 24gb via egpu on osx? Silly.
1
232
I wasn’t expecting that to really work at all, since without quantization there’s no real room for actually using the thing. But it’s loading and spitting back a token. Hah.
2
228
Prior experiment of bridging wgpu -> metal kernels <-> tinygrad -> back on osx shared mem was an interesting poc, (it worked!) just not practical for my splat tinkering. The stupid "but why?!" experiments will continue until morale improves or I learn something.
1
262
Ok. Interesting dive. Llama specifics and the Quant gap are outside my current wheelhouse of being able to reasonably guide, but still feeling bullish longer term, learned a few things about why my previous experiment is tricky to balance too.
1
284