Errthang is alive (@errthangisalive) header
Errthang is alive (@errthangisalive) profile picture

Welcome to DNN DeepNeuralNow reporting on the misused/abuse of #gan AI Confession #MLChurch Exploring data bias #AIEthics

Berlin, Germany
Joined May 2019
Photo by Errthang is alive (@errthangisalive)Photo by Errthang is alive (@errthangisalive)Photo by Errthang is alive (@errthangisalive)Photo by Errthang is alive (@errthangisalive)Photo by Errthang is alive (@errthangisalive)Photo by Errthang is alive (@errthangisalive)Photo by Errthang is alive (@errthangisalive)Photo by Errthang is alive (@errthangisalive)Photo by Errthang is alive (@errthangisalive)Photo by Errthang is alive (@errthangisalive)
Errthang is alive retweeted
ray-color 0.3.0 supports bloom. Gloomy sci-fi palettes, where the glow bleeds into the colors. I want to work on the UI a mit more!
5
6
1
58
4,302
Creative code is fun again #threejs
1
67
Growth from fire water process happy Diwali 🪔
1
122
possible worlds, wet paint settling to form an image using js
69
Errthang is alive retweeted
Upcoming Forge updates are 🔥
the next version of @ui8forge includes generative controls for your components in the chat.
1
4
1,517
one lesson each day, one experiment at a time
3
88
lay paint let it run bleed mix dry, layer by layer
8
study of fluid simulation
5
Errthang is alive retweeted
There's a buzzy new paper about GPT-6 Astra being able to directly interpret model weights (prompts full of floating point numbers) - I tried it with Qwen 3.8 27B on my laptop and found that, after 45+ minutes, that model could achieve the same thing simonwillison.net/2026/Nov/3…
422
443
113
5,438
342,411
Errthang is alive retweeted
Today, we open-source P-H3-Image, an image generation and editing model built from MiniMax-H3 by @MiniMax_AI. A SOTA video model, turned into an efficient open image model. - 𝗛𝗼𝘄 𝗲𝗳𝗳𝗶𝗰𝗶𝗲𝗻𝘁 𝗶𝘀 𝗶𝘁? Generate or edit images 5× faster, in 8 steps instead of 50. A 4 MP image takes 2.6 s instead of 12.4 s. The model is 7× smaller than H3, so high-resolution images are a light download and run on a much smaller GPU. - 𝗛𝗼𝘄 𝗴𝗼𝗼𝗱 𝗶𝘀 𝗶𝘁? Strongest at photorealism, documentary and editorial photography, film stills, and graphic styles with short quoted text. It renders 2 to 16 MP and edits with up to 8 input images. -𝗛𝗼𝘄 𝗱𝗼𝗲𝘀 𝗶𝘁 𝘄𝗼𝗿𝗸? We reworked every component of H3: the prompt upsampler, the text encoder, the diffusion schedule, the transformer, and the decoder. Use it with Diffusers or ComfyUI. 📄 Tech Report: pruna.ai/blog/oss-p-h3-image… 🤗 @huggingface Open Weights: huggingface.co/PrunaAI/P-H3-… 👉 @ComfyUI Native Support: huggingface.co/PrunaAI/P-H3-…
107
175
58
1,620
162,940
Errthang is alive retweeted
Drag-and-drop makes the digital graspable, but building it well is fiddly enough that many don’t bother. Declarative Dragging (with Josh Horowitz & Jeff Heer, #uist2026 best paper award), lets you make an element draggable just by listing the states dragging it can reach.
46
225
44
1,779
110,314
Khmer GAN v1 preview happy Cambodian new year
3
5
2
34
experiments #networkblending
1
1
1
4
a new piece for submission #neurips #classification #kbach
1
2
1
17
Errthang is alive retweeted
We asked GPT-6 Astra to edit Qwen3.5-0.8B weights to improve math. It directly changed only 0.016% of weights, fixing 0.8B's reasoning loops & improving math up to 6x and even instruction following 3x, without gradients or training. We call this Weight-Space Programming: frontier LLMs can now natively read/write neural network weights! 🧵 Blog: rikiyat.github.io/blog/weigh…
Readers added context they thought people might want to know
LLM was given weights explicitly as text in prompt and used code/forward passes (per authors' logs) to ablate Qwen looping direction, a known thinking-mode issue per model card. Primarily fixed repetition in that mode, not general 'natively' improving weights/math. rikiyat.github.io/blog/weight-sp… github.com/RikiyaT/lm_und… huggingface.co/Qwen/Qwen3.5-0… huggingface.co/RikiyaT/Qwen3.…
2,367
7,255
5,753
55,939
10,062,081
In 2019, Kate Crawford and Trevor Paglen trained a model only on the “person” categories of ImageNet. They called it ImageNet Roulette. A user uploaded a photo, and the model gave the person a label. excavating.ai/
1
46