正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

In 2010, @KimAsendorf dropped a pixel-sorting algorithm on GitHub. Free. Artists ran with it. A visual language emerged. 15 years later, Complex at Goethe Institut Bangkok reframes it: a pixel isn’t just an image, it’s a person, a city, billions of lives slipping out of control

Justin Gilanyi

7,506 subscribers

12,494 次观看 • 3 个月前 •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 条评论

暂无评论

原始帖子的评论将显示在这里

相关视频

GPT Image 2 is rolling out and... Wow. It just one-shot a grid of 100 completely unique pixel art items with meaningful labels in a single image. Prompt in the reply below 👇 More tests with pixel art and Image 2 to come. Follow for more.

GPT Image 2 is rolling out and... Wow. It just one-shot a grid of 100 completely unique pixel art items with meaningful labels in a single image. Prompt in the reply below 👇 More tests with pixel art and Image 2 to come. Follow for more.

proper

193,693 次观看 • 3 个月前

Spent the last few weeks building a pixel effects tool. What started as a side project with just image filters kept growing into presets, effects and here we are. Some of the best outputs came from just hitting Remix. 19 filters & 6 pixel effects. Drop any image. Walk away with something that feels like art. Try it out.

Spent the last few weeks building a pixel effects tool. What started as a side project with just image filters kept growing into presets, effects and here we are. Some of the best outputs came from just hitting Remix. 19 filters & 6 pixel effects. Drop any image. Walk away with something that feels like art. Try it out.

Blurr

43,552 次观看 • 1 个月前

🚀 New Paper: Pixel Reasoner 🧠🖼️ How can Vision-Language Models (VLMs) perform chain-of-thought reasoning within the image itself? We introduce Pixel Reasoner, the first open-source framework that enables VLMs to “think in pixel space” through curiosity-driven reinforcement learning. Current VLMs reason only in text — even when grounded in rich images or videos, their logical steps are verbalized in natural language. This restricts their ability to interrogate visual evidence and demonstrate how conclusions are drawn. 🔍 So we ask: What if we could make VLMs "show their work" by reasoning directly in the pixel space? Inspired by GPT-o3’s "think-in-image" ability, we propose a framework where VLMs use interactive visual operations — zoom, select-frame, highlight — to reason through complex visual inputs. To do this, we design a two-stage training process: Instruction tuning with synthesized visual reasoning traces. Reinforcement learning with curiosity-driven reward to balance exploration between pixel and text reasoning ✨ With this, Pixel Reasoner achieves near-SoTA performance on many information-rich multimodal benchmarks: 📊 84% on InfographicsVQA 🧠 84% on V* benchmark 🧩 74% on TallyQA-Complex It also achieves strong accuracy of 68% on MVBench (a video benchmark). Website: Paper: Code: Demo: (coming soon)

🚀 New Paper: Pixel Reasoner 🧠🖼️ How can Vision-Language Models (VLMs) perform chain-of-thought reasoning within the image itself? We introduce Pixel Reasoner, the first open-source framework that enables VLMs to “think in pixel space” through curiosity-driven reinforcement learning. Current VLMs reason only in text — even when grounded in rich images or videos, their logical steps are verbalized in natural language. This restricts their ability to interrogate visual evidence and demonstrate how conclusions are drawn. 🔍 So we ask: What if we could make VLMs "show their work" by reasoning directly in the pixel space? Inspired by GPT-o3’s "think-in-image" ability, we propose a framework where VLMs use interactive visual operations — zoom, select-frame, highlight — to reason through complex visual inputs. To do this, we design a two-stage training process: Instruction tuning with synthesized visual reasoning traces. Reinforcement learning with curiosity-driven reward to balance exploration between pixel and text reasoning ✨ With this, Pixel Reasoner achieves near-SoTA performance on many information-rich multimodal benchmarks: 📊 84% on InfographicsVQA 🧠 84% on V* benchmark 🧩 74% on TallyQA-Complex It also achieves strong accuracy of 68% on MVBench (a video benchmark). Website: Paper: Code: Demo: (coming soon)

Wenhu Chen

82,829 次观看 • 1 年前

Two years ago I made myself a badge with one of those cool Sharp in-pixel memory LCDs and a MAX 10 FPGA just for the heck of it. Made a few others (with a MCU) as commissions since then :)

Two years ago I made myself a badge with one of those cool Sharp in-pixel memory LCDs and a MAX 10 FPGA just for the heck of it. Made a few others (with a MCU) as commissions since then :)

Furrtek

151,653 次观看 • 2 年前

Google just dropped one of the most unique and creative ads that I’ve ever seen - right on the front page of an Indian newspaper - to promote their Pixel 9 phones. Just gave a look at how cool it is! #GooglePixel9

Google just dropped one of the most unique and creative ads that I’ve ever seen - right on the front page of an Indian newspaper - to promote their Pixel 9 phones. Just gave a look at how cool it is! #GooglePixel9

sid

43,606 次观看 • 1 年前

A GUY AT GOOGLE DEEPMIND MADE AN ISOMETRIC PIXEL-ART MAP OF NEW YORK CITY AND PUT IT ON THE OPEN WEB FOR FREE it's called you open the tab and the city is just sitting there in classic SimCity 2000 isometric pixel art. you scroll. and it keeps going. and going. i zoomed in on midtown and i could read the H&M signage in times square. in red. as actual pixel-art letters on the side of a building. i could see the crystalline spire of the Bank of America Tower poking out of a clump of skyscrapers. individual rooftop HVAC units. tiny green roof gardens. the little driveway loops in front of the hotels. he estimates the map needs roughly 40,000 tiles. nothing is a placeholder. the guy who made it is Andy Coenen, a senior staff engineer at Google DeepMind. he is not a pixel artist. by his own admission he is "a former electronic musician." what he actually did is kind of insane: > pulled NYC's geometry from the Google Maps 3D tiles API > fine-tuned an open-source image model (Qwen-Image-Edit) on ~40 hand-paired examples of "satellite tile → pixel art tile" > spun up 50 parallel instances on rented GPUs and generated tens of thousands of tiles in a few hours > the fine-tune cost him 12 bucks his own stated mission for the project, verbatim, is one sentence: "what's possible now that was impossible before?" apparently the answer is "one engineer can pixel-art most of a metropolis for the price of a sandwich." and the wildest part to me is he didn't sell it. no signup. no paywall. no NFT. you open the URL and the city is yours to wander. the post landed at 1,325 points on Hacker News and topped bestofshowhn's 2026 list. we live in a timeline where a senior engineer at one of the largest AI labs on earth spent his nights pixel-arting Manhattan for fun and then gave it away. the internet is healing.

A GUY AT GOOGLE DEEPMIND MADE AN ISOMETRIC PIXEL-ART MAP OF NEW YORK CITY AND PUT IT ON THE OPEN WEB FOR FREE it's called you open the tab and the city is just sitting there in classic SimCity 2000 isometric pixel art. you scroll. and it keeps going. and going. i zoomed in on midtown and i could read the H&M signage in times square. in red. as actual pixel-art letters on the side of a building. i could see the crystalline spire of the Bank of America Tower poking out of a clump of skyscrapers. individual rooftop HVAC units. tiny green roof gardens. the little driveway loops in front of the hotels. he estimates the map needs roughly 40,000 tiles. nothing is a placeholder. the guy who made it is Andy Coenen, a senior staff engineer at Google DeepMind. he is not a pixel artist. by his own admission he is "a former electronic musician." what he actually did is kind of insane: > pulled NYC's geometry from the Google Maps 3D tiles API > fine-tuned an open-source image model (Qwen-Image-Edit) on ~40 hand-paired examples of "satellite tile → pixel art tile" > spun up 50 parallel instances on rented GPUs and generated tens of thousands of tiles in a few hours > the fine-tune cost him 12 bucks his own stated mission for the project, verbatim, is one sentence: "what's possible now that was impossible before?" apparently the answer is "one engineer can pixel-art most of a metropolis for the price of a sandwich." and the wildest part to me is he didn't sell it. no signup. no paywall. no NFT. you open the URL and the city is yours to wander. the post landed at 1,325 points on Hacker News and topped bestofshowhn's 2026 list. we live in a timeline where a senior engineer at one of the largest AI labs on earth spent his nights pixel-arting Manhattan for fun and then gave it away. the internet is healing.

Nav Toor

439,138 次观看 • 1 个月前

Octo-Bouncer. Highly precise stepper motor driving with a Teensy 4.0 and custom pulse generating algorithm and PC based image processing with the goal of getting a machine to juggle a ping pong ball. [📍 bookmark for later to give it a try!] GitHub: ——- Weekly robotics and AI insights. Subscribe free:

Octo-Bouncer. Highly precise stepper motor driving with a Teensy 4.0 and custom pulse generating algorithm and PC based image processing with the goal of getting a machine to juggle a ping pong ball. [📍 bookmark for later to give it a try!] GitHub: ——- Weekly robotics and AI insights. Subscribe free:

Ilir Aliu

69,902 次观看 • 5 个月前

This is it! After 9 years of work, Pixel Art Academy finally got released also on Steam! If you ever wanted to learn pixel art, now you can do it in a video game as well:

This is it! After 9 years of work, Pixel Art Academy finally got released also on Steam! If you ever wanted to learn pixel art, now you can do it in a video game as well:

Retro 🎨🕹️🎮 Pixel Art Academy

154,328 次观看 • 1 年前

An image is nothing but a matrix of pixel values. Sending a photo through a pasta machine twice to obtain 4 understandable images from it, visualizing at the same time the principle on which Convolutional Neural Networks operate [📹 Kensuke Koike]

An image is nothing but a matrix of pixel values. Sending a photo through a pasta machine twice to obtain 4 understandable images from it, visualizing at the same time the principle on which Convolutional Neural Networks operate [📹 Kensuke Koike]

Massimo

1,607,971 次观看 • 2 年前

An ex-Tudor quant PM just sat down for 76 minutes and explained what's happened to the industry over the last 15 years. His main claim: there hasn't been a single new idea in trading in 15 years. Every algorithm and strategy moving billions through Wall Street today is a repackaging of something that already existed in 2010.

An ex-Tudor quant PM just sat down for 76 minutes and explained what's happened to the industry over the last 15 years. His main claim: there hasn't been a single new idea in trading in 15 years. Every algorithm and strategy moving billions through Wall Street today is a repackaging of something that already existed in 2010.

zostaff

13,637 次观看 • 2 个月前

This child predator abused victims across Asia & posted 100s of swirled-face photos online, believing the distortion made him untraceable. 🌀😱 A German forensic expert identified the swirl as a reversible math algorithm & painstakingly de-swirled the images pixel-by-pixel to reveal his face. Public release of the reconstructed image identified him as an English teacher in Korea. He fled to Thailand, but was arrested weeks later.

This child predator abused victims across Asia & posted 100s of swirled-face photos online, believing the distortion made him untraceable. 🌀😱 A German forensic expert identified the swirl as a reversible math algorithm & painstakingly de-swirled the images pixel-by-pixel to reveal his face. Public release of the reconstructed image identified him as an English teacher in Korea. He fled to Thailand, but was arrested weeks later.

End3of6Days9 (Helen) 🇺🇸

202,079 次观看 • 5 个月前

Take a look at Easymetric, an Aseprite plug-in by Oroshibu that makes creating isometric pixel art easy, giving the feel of 3D modeling inside a 2D tool. Check out what else it can do:

Take a look at Easymetric, an Aseprite plug-in by Oroshibu that makes creating isometric pixel art easy, giving the feel of 3D modeling inside a 2D tool. Check out what else it can do:

80 LEVEL

248,006 次观看 • 1 年前

🆕 Anthropic's Claude Opus 4.8 is now generally available and rolling out in GitHub Copilot. Early testing shows: • It demonstrates a clear step forward in code understanding and generation across a range of real-world coding tasks. • It handles complex problem-solving and large-codebase navigation with notable improvement to previous versions. Try it out in Visual Studio Code or Copilot CLI.

🆕 Anthropic's Claude Opus 4.8 is now generally available and rolling out in GitHub Copilot. Early testing shows: • It demonstrates a clear step forward in code understanding and generation across a range of real-world coding tasks. • It handles complex problem-solving and large-codebase navigation with notable improvement to previous versions. Try it out in Visual Studio Code or Copilot CLI.

GitHub

208,868 次观看 • 1 个月前

President Trump on Too Late Powell: "He's building a complex over there that is under his jurisdiction. He started it, and it's out of control. It’s billions of dollars for a little building. I could’ve done that building and made it beautiful for $25 million."

President Trump on Too Late Powell: "He's building a complex over there that is under his jurisdiction. He started it, and it's out of control. It’s billions of dollars for a little building. I could’ve done that building and made it beautiful for $25 million."

Trump War Room

42,506 次观看 • 4 个月前

GAME DEVELOPERS ARE OFFICIALLY COOKED this guy vibe coded a full pixel pirate sailing game that runs in the browser with opus 4.8 you sail a ship, engage in naval combat, explore the open sea, and interact with other ships works on mobile too a few years ago this would have been a full indie studio project with a team of artists, a sound designer, and 6 months of development now it's one person with claude code and a weekend game studios charging $40 for pixel art games while vibecoders are shipping them for free in the browser the barrier to making real games is completely gone

GAME DEVELOPERS ARE OFFICIALLY COOKED this guy vibe coded a full pixel pirate sailing game that runs in the browser with opus 4.8 you sail a ship, engage in naval combat, explore the open sea, and interact with other ships works on mobile too a few years ago this would have been a full indie studio project with a team of artists, a sound designer, and 6 months of development now it's one person with claude code and a weekend game studios charging $40 for pixel art games while vibecoders are shipping them for free in the browser the barrier to making real games is completely gone

Om Patel

80,031 次观看 • 1 个月前

In Indonesia 🇲🇨, there’s an unwritten rule: when an image appears on the back of a truck, it means real support from the people. Now look what’s on the move.. IRAN The truckers’ movement in Indonesia is strongly standing with Iran. This isn’t just a picture — it’s the voice of the people.

In Indonesia 🇲🇨, there’s an unwritten rule: when an image appears on the back of a truck, it means real support from the people. Now look what’s on the move.. IRAN The truckers’ movement in Indonesia is strongly standing with Iran. This isn’t just a picture — it’s the voice of the people.

Iran Embassy in Indonesia

550,018 次观看 • 3 个月前

I built a tool to create, animate & export pixel art using Figma & now it’s on a billboard in Singapore 🫨 It all started out as a joke & after 384 prompts in Figma Make….I DID IT Thanks Figma for all the love & for featuring it. It’s been my highlight of this year.

I built a tool to create, animate & export pixel art using Figma & now it’s on a billboard in Singapore 🫨 It all started out as a joke & after 384 prompts in Figma Make….I DID IT Thanks Figma for all the love & for featuring it. It’s been my highlight of this year.

Ayaneshu

23,195 次观看 • 8 个月前

Building a city takes vision, planning & years of work, something Mamata Banerjee delivered with New Town, Kolkata. Calling Kolkata a “city of slums” is easy. Creating a modern city from scratch isn’t. In just 15 yrs, New Town has transformed into a thriving urban hub boasting high-rise residences, IT & Fintech hubs, Top educational & healthcare institutions & tourist attractions.

Building a city takes vision, planning & years of work, something Mamata Banerjee delivered with New Town, Kolkata. Calling Kolkata a “city of slums” is easy. Creating a modern city from scratch isn’t. In just 15 yrs, New Town has transformed into a thriving urban hub boasting high-rise residences, IT & Fintech hubs, Top educational & healthcare institutions & tourist attractions.

নক্ষত্র | Nakshatra ❁

15,687 次观看 • 3 个月前