Cheng Lou @_chenglou

@pmddomingos The post this paper cites addresses this: x.com/_chenglou/stat…

Cheng Lou @_chenglou

3 months ago

Why Bother With Any of This Sudoku’s a classic SAT problem that’s exactly solvable by a traditional solver. But this involves 3 things: - Being able to spell out the rules in advance - Being able to formulate this as a clean SAT problem - Relying on a hyper-optimized solver

1 2 62 6K 7

@tszzl We should also aim to turn more traditional domains neural since models perf & power improves much faster than trad code. FSD didn't end up as 300M lines of LLM-written C++

OpenAI’s upcoming superapp overtaking the native ChatGPT Mac app (as opposed to the other way around) is an unsurprising but damning indictment of Apple’s failure to compensate for the distribution advantages of cross-platform UI toolkits through superior native UX It used to be that making a native Apple app was a point of pride (still is on iOS). But as design competence got democratized, Apple kinda stalled at solving the next frontier UI/UX/distribution problems (App Clip and Mac App Store were great ideas bottlenecked by corporate shenanigans). It shouldn’t be that indie devs have to defend a corporation’s stalls so much. After a decade they’d run out of steam and retire. Who’s next, Gruber? Oai has a high concentration of design chops and a proven, polished Mac app. If they decide against native desktop app then I hope Apple takes note, though it likely won’t anymore

See a (very accurate) Rothko for how the weather feels, wherever you are. rothko.joonas.wtf

Hey everyone — big day for us at Skiplabs: Skipper Beta is live 🚀 Skipper is a closed-loop coding agent. Instead of constantly going back and forth with the AI, you give it a spec and it iterates internally until it produces a working software service. We believe this is where AI-assisted coding is heading, and we’re excited to finally share what we’ve been working on behind the scenes. Start building with Skipper: skipperai.dev

@biosemiote Paper: arxiv.org/abs/2605.08605 Sotaku: x.com/_chenglou/stat…

Cheng Lou @_chenglou

3 months ago

I’m very happy to present my toy research project: Sotaku! It's a neural net that automatically discovered the rules of sudoku and learned to solve them, achieving a new state-of-the-art score of 98.9% on one of the hardest sudoku datasets, while being agnostic to the game, and

36 131 2K 227K 1K

Sotaku just got its first citation! Thanks @biosemiote! Really eager to see if there's potential in looped transformers. I still believe looping has interesting properties beyond just weight optimizations

What's the equivalent of A24 in the software industry? Consistently good indie-like outputs, not misled by successes, and challenging big players' directions

Pop Crave @PopCrave

3 days ago

‘Backrooms’ is now the biggest opening ever for an original horror film at $118 MILLION globally. Directed by 20-year-old Kane Parsons.

keyboard_arrow_left Previous keyboard_arrow_right Next

382 3K 59K 32.7M 4K

@suchenzang Is this what they meant by real recognizes real *badum tss*

Had a tab open for so long, the domain owner changed and it’s now a completely different site upon reload

@athasdev Sublime Text is still stable and running!

@asciidiego @nonzeroexitcode Prescribing update sparsity ruined creativity on the web because creativity relies on filling a larger state space

You either know your layout positions or spend a whole career documenting workarounds

We're hosting an event on June 16th in San Francisco. Compile is a one-day event that brings together engineers, researchers, designers, and builders of all kinds to discuss the future of software. cursor.com/compile

I remade the game Adventure Capitalist but its based in SF. You can also travel to Europe and China

Introducing DiffusionBlocks: Block-wise Neural Network Training via Diffusion Interpretation pub.sakana.ai/diffusionblocks What if we didn’t have to hold an entire neural network in memory to train it? Standard neural net training optimizes all parameters jointly. As a result, the memory required during training grows linearly with the depth of the network. In our #ICLR2026 paper, we propose DiffusionBlocks, a principled framework to train networks one block at a time, drastically reducing memory requirements while matching end-to-end performance. With DiffusionBlocks, we split the network into blocks and train them one at a time, so you only need memory for a single block. How? We explicitly assign each block a role: to move the representation a little closer to the target than the block before it did. That role turns out to be precisely what a diffusion model does, step by step. Each block only needs to optimize its own objective and can be trained independently. We validated this across five different architectures: • ViT • DiT • Masked diffusion • Autoregressive transformers • Recurrent-depth transformers In each case, performance is competitive with end-to-end training while using a fraction of the memory. This perspective also extends naturally to recurrent-depth (Looped) transformers, which apply the same network iteratively and normally require expensive backpropagation through time (BPTT). Viewed through DiffusionBlocks, we can replace those multiple iterations with a single forward pass during training. Read our paper and code, to learn more. Paper: arxiv.org/abs/2506.14202 GitHub: github.com/SakanaAI/Diffu… 🐟

Bryan has found someone to die for

Bryan Johnson @bryan_johnson

a week ago

I’m meeting Kate’s parents for the first time. Do you think they’ll like me? I’m flying 17 hrs. She’s from Australia and international travel increases aging. But I really love her so it’s worth the cost.

2K 280 27K 12.0M 2K

A Stanford psychologist spent 4 years proving that the simple act of walking generates 60% more creative ideas than sitting, and the experiment she designed to kill every alternative explanation is one of the most decisive findings in modern psychology. Her name is Marily Oppezzo. She got the idea for the study while walking with her advisor at Stanford to discuss her thesis topic, and the paper she eventually published in the Journal of Experimental Psychology in 2014 is sharp enough that it should have ended the seated meeting on the day it came out. She ran 4 experiments on 176 people. Same person tested twice. Once sitting, once walking. The creativity tasks were the standard ones psychologists have used for decades to measure how good a brain is at generating novel useful ideas. The result was almost too clean to publish. 81% of participants in the first experiment produced more creative ideas while walking than while sitting. In the second experiment, 88%. In the third, 100%. Every single person walked into a more creative version of themselves. On average, people generated 60% more novel useful ideas the moment their legs started moving. The skeptical question is the obvious one. Maybe it was the fresh air. Maybe it was the scenery passing by. Maybe it was the change of environment doing the work, not the walking itself. Oppezzo killed every one of those explanations with one experimental decision. She put people on a treadmill facing a blank wall. No scenery. No fresh air. No environmental change. Just legs moving in place while staring at white drywall. The 60% boost held. Then she ran the experiment that closed the case completely. She took participants outside in two conditions. Half of them walked through a Stanford courtyard. The other half were pushed through the exact same courtyard in a wheelchair. Same outdoor stimulation. Same scenery passing at the same speed. The only difference was whether the legs were moving. The walkers produced dramatically more novel high-quality ideas than the wheelchair group. The outdoors did almost nothing on its own. The walking did everything. This is the part of the study that hit hardest when I read it the first time. She also tested the opposite kind of thinking. Convergent thinking. The kind where there is one right answer and you have to narrow down to it. Word puzzles where 3 words share a hidden fourth word that connects them. The seated participants did slightly better on these. Walkers got slightly worse. Walking is not a general intelligence enhancer. It does one specific thing. It opens up the divergent search inside your brain. The part that generates options. The part that produces unexpected connections. The part that takes a problem and finds five ways into it instead of one. When you need to converge on the single right answer, sit down. When you need to find the answer in the first place, get up. The mechanism is now well understood. Walking selectively activates what neuroscientists call the default mode network, the system inside your brain that runs when you are not consciously focused on anything. The DMN is where mind-wandering happens. Where memories cross-reference each other. Where ideas that have been sitting in separate folders inside your head finally bump into each other. When you sit at a desk and force yourself to concentrate, you suppress the DMN. When you walk at a natural pace, the executive part of your brain gets just busy enough handling the walking that the DMN comes online and starts doing the work that focus was blocking. The most useful finding in the entire paper is the one almost nobody quotes. The boost did not turn off the moment people stopped walking. Participants who walked first and then sat back down stayed elevated. Their next round of seated creativity work was still significantly better than people who had been sitting the whole time. The rest lingered for at least several minutes after the legs stopped moving. You do not need to do creative work while walking. You need to walk before the creative work. The brain holds the state. The history of this is the part that should haunt anyone who still does meetings in chairs. Charles Darwin built a gravel loop behind his house in Kent called the Sandwalk and walked it 3 times a day for the rest of his life. The theory of evolution was developed one lap at a time on that path. Nietzsche walked up to 10 hours a day during the years he wrote his most important books and openly said the work was conceived on his feet. Beethoven composed for the morning and walked for 5 hours every afternoon with a pencil in his pocket for when something landed. Kahneman said the best thinking of his Nobel Prize-winning career happened on leisurely walks with Amos Tversky. Steve Jobs refused to take important conversations sitting down. He held them on foot. Every one of them was using the system Oppezzo would not measure until 2014. They just did not know what to call it. The question worth sitting with is the one almost nobody asks. Every meeting you have ever attended sitting around a table was a meeting held at a fraction of the brain power that was actually available to the people in the room. Every brainstorm that got stuck inside a conference room. Every problem you tried to solve at a desk and gave up on. Every idea you could not quite get to. The intervention is the easiest one in modern science. No supplement. No app. No subscription. No training program. Just a pair of legs and 15 minutes. The Stanford lab proved it. The philosophers knew it. The neuroscience explains it. And almost everyone reading this is still trying to think their way out of problems sitting completely still.

Boba tapioca balls/pearls are polymers. Their chewiness comes from long starch molecules tangled with water, and that structure changes when they are cooked, chilled, or reheated. I made a tiny interactive demo of the microstructure: leannchen86.github.io/matsci-cartoon…