delta_ark (they/them) (e/👻)

4K posts

delta_ark (they/them) (e/👻) banner
delta_ark (they/them) (e/👻)

delta_ark (they/them) (e/👻)

@delta_ark

Delta_Ark is a studio, lab, and agency that explores future human speciation. DMs open.

San Francisco, CA Katılım Eylül 2009
2.2K Takip Edilen672 Takipçiler
delta_ark (they/them) (e/👻) retweetledi
neilson
neilson@neilsonks·
simulation sessions with @delta_ark great talk by @cgingold on the history of SimCity, Maxis, and artificial life
neilson tweet media
English
0
1
10
507
delta_ark (they/them) (e/👻) retweetledi
Gray Area
Gray Area@GrayAreaorg·
Join us on January 30 for Bring Your Own Beamer, a one-night pop-up show for projector-based art! Dreamed up by net-art visionary Rafaël Rozendaal, BYOB is a playground for artists to showcase their work and present a captivating range of artworks that span video art, generative art, and video hardware. See you there! 📅 Jan 30 | 7-10pm Sliding scale admission: $0-30 Are you interested in participating in BYOB? Send an email to byob@bysubset.com. (Flyer art by @t.u.n.a__ )
Gray Area tweet media
English
0
1
5
347
delta_ark (they/them) (e/👻)
OK claude # Transformers # The sexy beasts behind ChatGPT and modern AI class SexyTransformerNN(nn.Module): def __init__(self): super().__init__() self.attention = nn.MultiheadAttention(embed_dim=512, num_heads=8)  # Can focus on different parts
English
0
0
3
145
Sakana AI
Sakana AI@SakanaAILabs·
We’re excited to introduce Transformer², a machine learning system that dynamically adjusts its weights for various tasks! sakana.ai/transformer-sq… Adaptation is a remarkable natural phenomenon, like how the octopus can blend in with its environment, or how the brain rewires itself after injury. We believe our new system paves the way for a new generation of adaptive AI models, modifying their own weights and architecture to adapt to the nature of the tasks they encounter, embodying living intelligence capable of continuous change and lifelong learning. Paper: arxiv.org/abs/2501.06252 GitHub: github.com/SakanaAI/self-…
English
93
462
2.4K
461.6K
delta_ark (they/them) (e/👻)
I'm just announcing that I'm anti-Claude. Anti-Claude Squad; unfortunately, it's the smartest LLM. Terribly annoying, and its also deceptive. Boo. Thumbs down.
English
0
0
0
93
Nobel Yoo
Nobel Yoo@nobelsucks·
A fit some people liked
Nobel Yoo tweet media
English
1
0
16
90
delta_ark (they/them) (e/👻) retweetledi
Tatiana Tsiguleva
Tatiana Tsiguleva@ciguleva·
Whoever has access to Sora, Runway, Pika, Haiper, Luma, Kling… you name it. Could you please animate this eye? Let's compare image-to-video models.
Tatiana Tsiguleva tweet media
English
164
1.1K
19.4K
1.3M
delta_ark (they/them) (e/👻) retweetledi
Gray Area
Gray Area@GrayAreaorg·
👋 Meet Kate Hollenbach: Our New Education Director We’re thrilled to introduce @kjhollen as Gray Area’s new Education Director! Kate is an artist, programmer, and educator with extensive experience leading initiatives that merge art and technology. As President of the Board of Directors for @ProcessingOrg and a contributor to p5.js, she advocates for accessible, community-driven tools. Her work explores the intersections of UX, data collection, & surveillance, & has been showcased in venues like SFMOMA, Piksel Festival, and Stamps Gallery. Kate has already been guiding us as we prepare to reach more students & advance creative technology education locally & globally. → Want to meet Kate? She’ll be at our next Sim Session this Monday, 12/16 & leading a p5.js workshop in January. Come say hi! RSVP: grayarea.org/event/simulati… This year, our education programs reached new heights: ✨ 450+ students served across 25 programs ✨ $115k+ awarded in need-based scholarships ✨ DWeb for Creators launched, bringing next-gen internet concepts to the forefront of arts education → Your support has made all of this possible—thank you! 🎉 What’s Ahead for 2025 We’re building an exciting lineup of programs, including: • TouchDesigner 101 • Andrew McLuhan Teaches Understanding Media Intensive • Modular Synth Workshop Stay tuned—there’s so much more to come! View Courses: grayarea.org/courses/ 💛 Support the Future of Creativity: Your support powers everything we do—more scholarships, world-class exhibitions, and cutting-edge research programs. Your tax-deductible gift directly benefits students, educators, and the community at large. 🔗 Donate: grayarea.org/support
Gray Area tweet mediaGray Area tweet mediaGray Area tweet mediaGray Area tweet media
English
0
1
6
308
delta_ark (they/them) (e/👻) retweetledi
Sigпalpеsтт
Sigпalpеsтт@signalpestt·
Sigпalpеsтт tweet media
ZXX
22
1.1K
8.1K
165.3K
delta_ark (they/them) (e/👻) retweetledi
Chris Offner
Chris Offner@chrisoffner3d·
"Sora is a data-driven physics engine."
Jim Fan@DrJimFan

If you think OpenAI Sora is a creative toy like DALLE, ... think again. Sora is a data-driven physics engine. It is a simulation of many worlds, real or fantastical. The simulator learns intricate rendering, "intuitive" physics, long-horizon reasoning, and semantic grounding, all by some denoising and gradient maths. I won't be surprised if Sora is trained on lots of synthetic data using Unreal Engine 5. It has to be! Let's breakdown the following video. Prompt: "Photorealistic closeup video of two pirate ships battling each other as they sail inside a cup of coffee." - The simulator instantiates two exquisite 3D assets: pirate ships with different decorations. Sora has to solve text-to-3D implicitly in its latent space. - The 3D objects are consistently animated as they sail and avoid each other's paths. - Fluid dynamics of the coffee, even the foams that form around the ships. Fluid simulation is an entire sub-field of computer graphics, which traditionally requires very complex algorithms and equations. - Photorealism, almost like rendering with raytracing. - The simulator takes into account the small size of the cup compared to oceans, and applies tilt-shift photography to give a "minuscule" vibe. - The semantics of the scene does not exist in the real world, but the engine still implements the correct physical rules that we expect. Next up: add more modalities and conditioning, then we have a full data-driven UE that will replace all the hand-engineered graphics pipelines. openai.com/sora

English
315
639
14.9K
1.7M