There is a tiny used bookstore near the Navy base in Yokosuka. Mrs. Kuroda has run it for 36 years. Every summer, American Navy families get transferred. They can't take everything with them. So they sell her their books. She says Japanese books come back clean. American books come back with the family still inside. She has kept everything she ever found in them. Three cookie tins. 1,184 things. She let me read them. A grocery list on the back of a church bulletin: milk eggs call Mom PRAY FOR THE HENDERSONS ice A biscuit recipe on a card, tucked in a cookbook. At the bottom, in a different pen: "DO NOT give this to Aunt Patsy." A two-dollar bill, folded into a tiny square, inside a child's Bible. "For emergencies. Love, Grandma." Mrs. Kuroda has found eleven of these. Not one was ever spent. A Little League schedule. Every game circled. Next to three of them, in a man's handwriting: "OFF WORK." Next to the playoff game: "Swapped shifts with Rick. Worth it." Inside the cover of a mystery novel: "Dad, I finished it first. The butler did it. Love you. Jess" A note on hotel stationery, in a paperback: "If you found this, I hope your day gets better. Kayla, age 11, Ohio" She sells almost everything. Not this one. A children's picture book, worn soft. Inside the back cover, someone drew a calendar by hand. 214 little boxes. Each one crossed out in crayon, one X a night. In September the X's are giant and crooked. By March they're small and neat. You can watch a kid learn to write. Next to the last box, in a man's handwriting: "Last one, buddy. See you tomorrow." And under that, in crayon letters so big they run off the page: "HE CAME HOME" A Navy family sold it to her in 2011, in a box of forty books marked KIDS. She doesn't think they knew it was in there. It has sat open on her counter for fifteen years. Young sailors come in, read it, and go very quiet. Then they buy something they don't need, so they can stand there a little longer. I asked her what 36 years of American books had taught her. "Japanese people write in books so they remember what the book said," she told me. "Americans write in books so somebody remembers them."

Robotics deep dive: HUMANOID CHOKEPOINTS Almost every supply-chain post about humanoids has one country in it. Trace five critical inputs one at a time and they land in four different places. Magnets first, because that is where the argument usually stops. Every high-torque joint runs on sintered NdFeB, and on the IEA's 2024 figures China holds 91% of refined output and 94% of sintered permanent magnets, against 60% of the mining. Mining is the distributed part, and the chokepoint is the chemistry. The precision reducer is the node almost nobody names. Nabtesco states on its own site that it holds approximately 60% of the global market for the precision reduction gears in industrial robot joints. Harmonic Drive Systems is the incumbent on the strain-wave side. Both Japanese, both sitting on decades of gear grinding, heat treatment and yield that nobody has replicated at price. There is no mine to open here. Optimus runs 14 linear actuators; per-robot screw counts get estimated anywhere from 14 to more than 40, at $1,350 to $2,700 each. A planetary roller screw is a micron-tolerance ground part, and only a handful of firms anywhere make them to that standard: Japanese, German, Swiss, with Chinese entrants scaling into it now. The constraint is grinding capacity and the people who can run it. Compute inverts the picture. Nvidia designs Jetson Thor in California and cannot manufacture it. Roughly 92% of the world's sub-10nm logic capacity sits on one island. Battery cells go back to China: over 80% of global cell capacity, about 99% of LFP. A McKinsey component map, reported by Forbes in June, puts it the same way: China is overwhelmingly dominant in exactly one category, magnets for motors, while bearings, driver boards and sensors have suppliers in several countries. So it is four dependencies, held by parties with different export regimes, different politics and no shared interest in coordinating. A supply chain with one chokepoint is one negotiation. Reshoring the magnets still leaves you asking Japan for the gearboxes and Taiwan for the brain.

2 hours 43 minutes. 442 steps. 5,406 lines of code. The page still does not load 💀 I gave Qwen3.8 Flash Next my standard bench prompt: a voxel Japanese pagoda garden in Three.js, 16,500 voxels, modular source, run it and screenshot it when it's done. Other models finish this one easy. It never opened a browser. Never started the dev server. Never counted a voxel. It spent the entire run fighting its own export statements. petals.js got rewritten 19 times. Not patched, rewritten from scratch every time. water.js 9 times, palette.js 11, lanterns.js 7. It was loop between exactly 2 errors: Export 'update' is not defined in module. 53 times. Duplicate export of 'createPetals'. 10 times. Add the alias and you get the duplicate. Remove it and the export goes missing. In the last 70 steps it flipped between those 2 states 9 times. Twice it deleted the file and wrote it back identical. 85 writes against 7 reads. It almost never looked at what was already on disk. It compacted its own context 4 times and came back to the same 2 errors every time. It stopped with 3 files still failing node --check, all on the same line, update as updatePetals. 2 modules that main.js imports do not exist at all, and one of them is the lanterns file it had written 7 times. Then I gave the same model the same prompt as a single HTML file. It shipped a complete working scene in 1 pass. So it is not a capability wall. The module code it wrote is decent. It cannot hold its own module graph together, and it has nothing that tells it that it is going in circles. 438,737 output tokens and it never once said it was stuck. I spent 3 days making this thing run on my rig. An FP8 KV cache path that vLLM rejects on Ampere in 4 separate places. The 51B n-gram table baked down to FP8 so it fits in host RAM. W4A16 weights, the full 262K context, on 4 gaming GPUs from 2020. All of that works. And then it cannot wire 16 files together. So I'm going back to Qwen3.8 27B as my daily driver until something changes. Could be something in my own build doing this, I'm rebuilding the quant to find out. Either way I'll post what comes back.

My college friend Nakamura lives in Sasebo, a small city in southern Japan with a U.S. Navy base. This fall, at his daughter's elementary school sports day, every adult on that field cried. Including the principal. Next door to Nakamura lives an American Navy family. The father is Brandon. A chief petty officer from Alabama. Big, loud, kind. His ship is based in Sasebo. Last spring, the ship left for a seven-month deployment. Brandon left behind his wife, Amber, and their eight-year-old son, Jackson. Jackson goes to the local Japanese elementary school. He's the only American kid there. On Jackson's bedroom wall, there was a paper chain. One link for every day until his father came home. Every night before bed, he cut one off. Nakamura's own father died when he was six. He told me once that at every school sports day, there was an empty spot next to him. Everyone else had a dad. He had a space. So when Brandon's ship left, Nakamura quietly took the spot. He doesn't really speak English. He didn't need to. He taught Jackson to ride a bike in the parking lot. He played catch with him every Sunday. He checked his math homework, which was in Japanese, which Jackson's mom couldn't read. When Jackson had a bad day, Nakamura took him for ice cream and they sat there, not talking, two guys eating ice cream. In Japan, every school sports day has a parent-child three-legged race. Jackson was supposed to run it with his dad. So Nakamura said he would run it with him instead. On the day, Jackson's paper chain still had 47 links left. At the starting line, Nakamura knelt down and tied his ankle to Jackson's with a white cloth. Jackson was trying hard not to look sad. All the other kids had their dads. The teacher raised the starting pistol. Then somebody near the school gate started to clap. A man was walking across the field. White Navy uniform. Sea bag over his shoulder. Brandon. His ship had come back 47 days early. He had told exactly three people. His wife. The principal. And Nakamura. Nakamura didn't say anything. He just knelt down, untied the cloth from his own ankle, and held it out to Brandon. Jackson turned around. He froze. For a long second, he didn't move at all. Then, very quietly: "Daddy?" And he ran. He was still half-tied to nothing, the white cloth flapping from his ankle. Brandon dropped the sea bag and went down on his knees on the dirt, and Jackson hit him so hard they both almost fell over. Neither of them said a word. Brandon just held him, with his hand on the back of Jackson's head, rocking a little. His shoulders were shaking. Nakamura says the whole field went silent. Four hundred Japanese parents, kids, teachers. Then he heard it. People crying. Grandmothers. Fathers with video cameras. The principal, into a microphone that was still on. Then they ran the race. Brandon and Jackson, tied together at the ankle. They fell down twice. They came in dead last. Every single person on that field stood up and cheered like it was the Olympics. Afterward, Brandon found Nakamura by the bleachers. They can't talk to each other. Not really. So Brandon reached into his pocket and pulled out a coin. A challenge coin from his ship. In the U.S. military, it's what you give someone when "thank you" isn't big enough. He put it in Nakamura's hand and shook it. He held on for a long time. Nakamura bowed. All the way down. Brandon stood up straight and saluted him. Nakamura keeps that coin in his wallet now. I asked him once why he did all of it. Eight months of bikes and homework and ice cream for somebody else's kid. He looked almost embarrassed. "I wasn't his father," he said. "I was just keeping the spot warm until his father came home." That day, I think that field had two heroes on it. One came home from the sea. The other one had been there the whole time.

Can it run Doom?” is old news. Now it’s “Can it play Doom?” An AI deciding every step it takes, live on Android phones all around the world on the Acurast network. One open model, one phone per move, 0.7 s per decision. Argentina, Japan, wherever the network is. Decisions, decentralized. Try it out, explore the other demos, or create your own Laya instance 👉

# OpenCode Features and Practical Usage 📜 Tired of re-explaining your project's conventions every single session? `AGENTS.md` fixes that: write it once, and the agent always operates with your rules in mind. 🏷️ Title: AGENTS.md 🔗 URL: 📘 Overview `AGENTS.md` is the file you use to give OpenCode custom instructions. Document your project's conventions, architecture, and build steps there, and that content is always included in the LLM's context so the agent behaves the way your team expects. ⚙️ How It Works Rules live at two levels: ・Project-level: an `AGENTS.md` at the repo root, applied only within that directory tree. ・Global-level: `~/.config/opencode/AGENTS.md`, shared across all sessions and best for personal preferences. At startup OpenCode searches in order: local `AGENTS.md` or `CLAUDE.md` (walking up from the current directory) → global `~/.config/opencode/AGENTS.md` → the Claude Code compatibility file `~/.claude/CLAUDE.md`. The first match in each category wins. The design is close to Cursor-style rules and makes migration easy. 🛠️ Practical Usage To pull in external docs as instructions, list them in the `instructions` field of `opencode.json`, e.g. `"instructions": ["CONTRIBUTING.md", "docs/guidelines.md", ".cursor/rules/*.md"]`. Globs are supported. If writing from scratch feels like a chore, run `/init`: it scans important files, may ask targeted questions, and generates or improves `AGENTS.md` for you. Commit the result to Git so the whole team shares it. 💡 Use Cases Capture tacit knowledge like "commit messages in Japanese," "tests use pytest," or "never import this layer directly" in `AGENTS.md`, and both new teammates and the agent share the same assumptions, cutting down on review churn. In monorepos, `instructions` globs let you bundle per-package conventions. ⚠️ Caveats File references hand-written inside `AGENTS.md` are not expanded automatically. When you need multiple files reliably loaded, the `instructions` field of `opencode.json` is the dependable choice. An existing `CLAUDE.md` is recognized for compatibility, but consolidating new content into `AGENTS.md` keeps things tidy. Remote URL references carry a 5-second timeout. #OpenCode# #AGENTSmd#

A TON OF THINGS HAPPENED IN THE STOCK MARKET TODAY. Here's a full recap: 1. Tesla $TSLA rose 5% today, marking its best day since early July. The move comes ahead of Tesla’s upcoming Cybercab Launch Event, where investors will be watching for concrete updates on robotaxi deployment, Cybercab production, autonomy progress, and whether Tesla can turn the vehicle from a concept into a real revenue-generating fleet. Tesla has already disclosed that Cybercab production has started, with public-road engineering tests and employee rides beginning at Giga Texas. The key question is whether the event delivers actual deployment details rather than another demo, including timing, fleet size, city expansion, and cost-per-mile economics. 2. Treasury Secretary Bessent today at the G20 summit said he believes the Japanese government and Bank of Japan will take actions that lead to a stronger yen. On the Fed, he said he would not speculate on what policymakers may or may not do, but added that traditionally “you don’t raise into a supply shock.” On bonds, Bessent said he and Warsh are “on the same page,” while noting he does not believe he can change the market’s equilibrium price. He also said Trump believes Iran is not ready to make a deal yet, and that Operation Outcast is aimed at creating conditions that bring Iran back to the table. 3. Anthropic has reportedly signed a $35B cloud deal with Lambda, an Nvidia-backed cloud provider, according to WSJ. The twist: Nvidia $NVDA is effectively the landlord. The data center is being built by Hut 8 in Nueces County, Texas, and Nvidia signed its own agreement with Hut 8 a few weeks ago to lock down the capacity. Lambda will use that space to run chips it bought from Nvidia, which is also one of its investors. The deal highlights how Nvidia is extending its role beyond selling GPUs and deeper into the AI infrastructure stack with financing, capacity access, cloud partners, and the physical data center footprint behind frontier AI demand. 4. The FTC and 22 states are reportedly preparing to sue Amazon $AMZN over alleged secret ad price hikes. The FTC is expected to claim Amazon manipulated its ad auctions by inserting its own “soft reserve” bid above the runner-up bid, effectively raising the minimum price advertisers had to pay. The practice allegedly began in 2018 and generated tens of billions of dollars over 7 years. In recent years, Amazon allegedly used the mechanism to raise minimum bids 70%–80% of the time, with the FTC claiming it increased pay-per-click costs by as much as 50% on major shopping days. Amazon generated $68B in advertising revenue in 2025, and this would mark the FTC’s third major case against the company after its Prime case and ongoing monopoly lawsuit. 5. Retail investors bought roughly $250M of Nvidia $NVDA shares on Wednesday, their 3rd-largest daily purchase since mid-May. That extended the retail buying streak to 15 consecutive trading sessions, with investors purchasing more than $2.5B of Nvidia stock over that period. For context, the largest daily retail purchase came in late February at about $1.0B. Over the last 12 months, retail investors have bought roughly $30.0B of Nvidia shares, the most of any Magnificent 7 company. 6. The White House published details of the U.S.–Venezuela oil deal, saying Venezuela has granted North American Blue Energy Partners 100-year concessions for 17 oil fields. The fields reportedly contain roughly 65B barrels of proven oil reserves, while NABEP plans to invest up to $100B into Venezuelan oil infrastructure to rapidly increase production. As part of the deal, the U.S. government receives a 35% equity stake in NABEP’s parent company at “zero cost to taxpayers,” the right to purchase 20% of all current and future production at production cost, and the right of first refusal on the remaining 80%. The U.S. also gets veto power over board appointments, with a majority of NABEP’s board required to be U.S. citizens. Venezuela is expected to receive roughly $200B in royalties and tax payments over the first 25 years, while the White House is calling it the “biggest oil deal in world history.” 7. U.S. annual interest expense has climbed to a record 18.5% of federal government revenue, officially surpassing the prior record of 18.4% set in 1991. This share has more than quadrupled over the last 4 years as interest costs on public debt have surged. Annual interest expense now stands at a record $1.25T, more than 4x the level seen in 1991. Meanwhile, the 30-year Treasury yield is trading around 5.21%, just 13 bps below its highest level since 2007. For context, the 30-year yield was around 8.00% in 1991, highlighting how much larger the U.S. debt burden has become. 8. BofA reiterated its Buy rating on Meta $META with an $810 price target, highlighting the potential launch of Meta’s consumer AI agent Hatch in early September inside Instagram and WhatsApp. Hatch can reportedly browse websites and navigate user interfaces to complete autonomous tasks like purchases, restaurant bookings, form filling, and communications. Meta is also reportedly targeting an October launch for its new AI model, Watermelon, which has shown frontier-level performance on certain internal benchmarks, with Hatch expected to integrate Watermelon’s automation capabilities after launch. BofA sees a major long-term opportunity in consumer AI agents, with Meta’s global user base giving it a significant adoption advantage, but said success will depend on ease of use, real utility, ecosystem integration, user trust around automation and security, and subscription pricing that creates consumer value while earning a return on Meta’s compute investment. 9. The top 10 most active options today by contracts traded were $TSLA with 4.4M contracts, $NVDA with 3.3M contracts, $AAPL with 1.3M contracts, $AMZN with 1.0M contracts, $MU with 952K contracts, $META with 606K contracts, $SPCX with 561K contracts, $INTC with 470K contracts, $PCG with 460K contracts, and $GOOG with 453K contracts. 10. Trump said interest rates are “too high” and said he has “a lot of respect” for Fed’s Warsh, adding that Warsh will “do what he has to do.” On Iran, Trump said any strikes would be limited, while noting that a lot of oil is still coming out of the Strait of Hormuz. He said ships came through Hormuz last night with Navy assistance and that the U.S. is averaging about 30 ships per night out of the Strait. Trump also said Iran “doesn’t know who the leader is,” adding, “we’ll see what happens.” 11. Take-Two $TTWO fell 7% as GTA 6 leaks continued ahead of the November 19 release. Recent leaked footage has reportedly shown combat, vehicle theft, the return of the six-star wanted system, a biplane flight over Vice City, and a 4.5-minute Lucia story clip. The pressure reflects growing concern around how much of the game is being revealed before launch, even as GTA 6 remains one of the most anticipated releases in gaming history. 12. China’s CXMT has reportedly started small-scale production of HBM3E, the advanced memory used in AI processors including Nvidia’s H200 and Blackwell GPUs, according to The Information. Alibaba’s T-Head and Cambricon are already testing CXMT’s HBM with their AI chips and could begin using it in products as early as 2027, with CXMT planning to expand production next year. The development could ease a key bottleneck for China’s domestic AI-chip industry, which remains restricted from buying the most advanced foreign HBM. The caveat is that CXMT is still facing low yields and remains roughly 3–5 years behind the leading HBM players, while $SKHY SK Hynix, Samsung, and Micron $MU are already mass-producing HBM4 and sampling HBM4E. WALL STREET IS THE GREATEST SHOW ON EARTH.

xdce-crowd-sale:native is down about 7% over the past 30 days, but it’s been anything but quiet for XDC Network (@XDCNetwork). MoneyGram and Taurus moved into the validator set, Robinhood opened the door to US retail users, and SBI’s Japan push picked up pace. Here’s what happened: [Oct 7] Digital asset infrastructure firm Taurus joined XDC as an institutional validator. [Oct 8] Japan’s CoinTrade began offering XDC to its users. [Oct 8] Robinhood (@RobinhoodApp) listed XDC for eligible US customers. [Oct 14] XDC’s AI payments marketplace rebranded from XDC AI to XDC SI. [Oct 15] MoneyGram (@MoneyGram) announced it will run a validator node on XDC Network. [Oct 20] SBI XDC, SBI VC Trade (@sbivc_official) and Shinhan Card signed an MOU to explore yen stablecoin payments between Japan and South Korea. [Oct 27] XDC released v3.0.0-testnet-2, adding a proportional validator reward fork on testnet. [Oct 30] SBI XDC and Socialpath were selected for a Japanese government project using XDC to verify communications from financial institutions. [Nov 2] XDC Ventures (@XDCVentures) invested in ScallopX to bring XDC and USDC to cards and payouts across 70+ markets.

Every summer, our town borrows twelve American teenagers. We have had a sister city in Michigan since 2001. For 26 years, my aunt Fumie has run the exchange. Every July, twelve kids from Michigan spend three weeks living with Japanese families who have never had an American in the house. Americans keep telling me they're worried about their kids. The phones. The manners. "Kids these days." So I asked my aunt to ask our host families one question. "What do you remember about your American kid?" Forty-one families answered. "He thanked me for every meal. Then he thanked me for the thank-you. In three weeks, I was thanked more than in thirty years of marriage. My husband has been informed." (Host mother, 52) "She hugged my mother-in-law on the first day. My mother-in-law is 88. Nobody had hugged her since the 1960s. Every spring she asks if 'the hugging one' is coming back." (Host mother, 47) "He washed my car. No one told him to. He said his dad always told him, 'Leave it better than you found it.' The car is fourteen years old. It has never been this clean. Neither have I, emotionally." (Host father, 58) "Our son is very shy. He has never brought a friend home. Day one, the American boy decided our son was his best friend. Our son did not get a vote. Five years later, they still play video games every Saturday. Six thousand miles apart." (Host mother, 44) "She asked my father about the war. In our family, nobody asks. He talked for two hours. She cried. He cried. Then she asked if he wanted to see her basketball highlights. He did. He watched all of them." (Host mother, 50) "She called me 'Mom' on the third day. I told her I'm not her mother. She said, 'I know. I've got one of those too. She says hi.'" (Host mother, 49) "At the farewell party, he gave a speech in Japanese. Every word was correct. Every word was in the wrong order. Our whole town cried." (Host father, 55) Then my aunt sent one more thing. Not an answer. A count. Twenty-six summers. 312 American teenagers. "Every year," she wrote, "somebody tells me American kids today are rude. Spoiled. Glued to their phones. I have had 312 of them in this town. Not one was rude. Not one. All 312 left their rooms cleaner than they found them. All 312 said thank you more times than we could count. And every single summer, at the airport, it is the Japanese who cannot let go." This July, one of the twelve was a girl named Paige. Sixteen. Her father came in the very first group, in 2001. He stayed with the Kawabata family. Paige asked to stay with the Kawabatas. Mrs. Kawabata is 77 now. She put Paige in the same room. She made the same curry. On the last night, Paige stood at that same table and said, in careful Japanese, the sentence her father had taught her on the plane. "Osewa ni narimashita." Thank you for taking care of me. The exact words he had said, in that exact spot, in 2001. Mrs. Kawabata says she had to leave the room. So, America. You can stop worrying so much. We've been borrowing your kids for twenty-six years. We kept count. You did good. (The 88-year-old mother-in-law has already put in her request for next July. Two huggers.)

i think personalisation is about to become the biggest differentiator in llms, and not the kind most people think of. most people mean an assistant that remembers your name and what youve typed in the box previously. i mean one that already knows what you did and what you like before you ask it anything. @myrad_hq's already built that part. it skips the box entirely, it just reads what you did. > ask it what to eat tonight and it skips past japanese, since you've already ordered it four times this week, and puts mexican in front of you instead > ask for a gym routine and it already has your strava, three runs after work tuesday wednesday friday, two rides the other days, so it builds strength around the days you're already spent instead turning your legs to jelly before tomorrows run. > ask for a spending audit and it already knows your uber rides spiked the same week your food app orders doubled, so it flags the actual pattern instead of making you dig through two apps most chatbots guess from what you say. the myrad approach is reading what you did and never hallucinating based on inputs 3 context windows ago. your data mode is walled off, wallet gated, nobody else's data touches yours. the verification underneath runs on zero knowledge proofs, it confirms you actually watched something, rode somewhere, ordered something, without myrad ever holding your netflix password or logging into the account itself. proof of the activity, never custody of the account. this is what personalisation actually evolves into, not a memory feature bolted onto a chatbot, the actual next layer underneath every ai product built after this one. now picture that same verified context sitting inside a humanoid assistant instead of a chat window, one that already knows your routine and your habits before it opens its mouth to ask you anything. myrad is building for the future base:0x693bad964f815f32fabe0b9d4911865bffc30172