与「reading」相关的搜索结果

X AI ALGORITHM UPDATE (BIG ONE) 🚨 X updated their open source algorithm yesterday and the biggest number in it is gone: copy link went from 20 to 0 points. Small accounts should focus on: posts people like, reply to and stay on (so stop counting on link copies) tl;dr: - on Nov 13 X's open source code set the score for copying a post's link to 0 - copy link: 20 → 0 - it was the top score in the whole system, 4x a reply - the code also names a "copy link bait" spam check - likes (0.708), replies (5) and DM shares (5) didn't move full details: - The number that's gone Since I started reading X's open source code in August, one number sat at the top: 20, for someone tapping share and copying your post's link. Nothing else came close. As of the Nov 13 release, it's 0. X still guesses who'll copy your link. It just multiplies that guess by 0 now. X didn't explain it. It's just what the code says. (I check the open source algo daily with Claude and share updates with you) - Cross it off your list My own checklist called copy link the biggest number. Last week's post said it too. It was true then. It isn't now. If you saved that list, cross that line out. - The "copy link bait" check X's code now mentions a spam check called "copy link bait". In the code it adds a spam label to the post, and that label already keeps a post out of strangers' feeds. It only shows up in a test, so I can't see if it's running or how strict it is. My read: X saw people baiting link copies, so it turned the score off and built something to catch the bait. That's a read, the code doesn't say why. - Why that matters if you're small If your plan was posts people copy the link to, that plan now earns 0 in X's ranking. A copied link can still bring people in from outside X. It just doesn't push your post up anymore. What still pays: likes at 0.708 (the highest ever), people staying on your post, replies at 5 and back and forth with mutuals at 20. - Also new: photo and video tags If a post has a spam label, people you tag in its photo or video who don't follow you won't get notified. Same idea as last week's rule for replies. - What didn't change Every other score. Your new posts still get their extra push in the first 2 hours and first 200 views, and early likes still pick which one gets it. Here's a recap of what you should be doing: - aim for likes, replies and time spent, the copy link score is gone - a DM share still earns 5, same as a reply or a quote - likes sit at 0.708, never higher - time on your post keeps counting at its best rate yet - 10+ seconds after someone taps in adds 0.385 - write your replies yourself, under big accounts most of all - give people a reason to hang around your profile - in videos the opening seconds carry it, an open alone scores 0 - posts read to the end help X find you strangers - smaller accounts (below 50K) get a shot at a spot near 16 for a fresh original - early likes decide which new post gets that spot - post when your followers are awake, the push lasts 2 hours and 200 views - mutuals going back and forth earn 20, so follow back the regulars - only your originals ever get shown to strangers - like 1 and like 32 each unlock another way to reach strangers - one strong post per feed, your second only counts 62% - clips longer than 10 seconds for the video lists - a post likely to win you a follow gets +4 - give your pinned post a look, it can affect the whole account What you should NOT be doing: - counting on copy link shares, they score 0 now - baiting link copies, the code names a spam check for exactly that - a spam label also stops your photo tags reaching non-followers - AI-written replies under big accounts, "llm slop" is a flag X uses - copy-paste replies, labeled ones skip non-followers' notifications - chasing taps, 0.274 and dropping - drifting off your topic, each probable "not interested" takes 53.07 away - videos people open and leave, the open itself earns 0 - posting at 3am, it wastes the 2 hour push - expecting replies and reposts to reach strangers - an insult label, it hides that post from non-followers - earning a misinfo or low quality label, which adds a warning and locks strangers out of liking or sharing - 3 adult photos or videos among your latest 5 posts, that puts a label on you - forgetting videos get rechecked at 64 and 512 likes - one account label and strangers stop seeing you - pinning a link to a site X rates badly, that can mean a label for a week - posting your own old words again risks the copypasta flag - a low quality link plus tagged strangers reads as spam - bait for engagement, big or small it gets a label - several posts back to back, they split the same feed - hashtag piles, they do nothing - bookmarks for reach, they score 0 - hoping a 3 day old post still lands in For You, it stops at 2 days

I LAUNCHED A GROK BOT TERMINAL OVERNIGHT, GAVE IT $44.82 AND STOPPED ASKING AI WHAT IT WOULD DO. BY MORNING IT HAD $11,643.21 AND SIX AGENTS LOGGING EVERY TRADE I spent a year asking agents what they'd trade and watching the chat scroll. Last weekend I built the thing that actually trades, in Grok Bot, with no code I touched by hand. The six agents share one screen, each one job: > scanner reads new token pairs and volume spikes > rug check filters suspicious tokens before anything executes > sizer sets position from account equity, not a fixed ticket > executor opens and closes with slippage tracking > logger writes the reason behind every trade > equity curve updates on every close I went to bed on $44.82 and left the laptop open on the dashboard. By morning the balance read $11,643.21. Every trade on the activity feed had a reason next to it and a line in the log. That's the shift I didn't see coming. Not that an agent made money overnight. That I stopped being the one asking "would you long this?" and started being the one reading the log of what already happened. Starting balance: $44.82 Current balance: $11,643.21 Grok Bot built the terminal, the agent architecture and the dashboard. I described what I wanted and the thing went live. The full build is in the article below ↓ The whole build is in the post below ↓ Comment " Grok_Bot " 2️⃣ Like and Repost 3️⃣ Follow me @Nexa_Tech_Ai I'll DM you the complete setup.

You want to know what frustrates the hell out of me? Putting your heart, your art, your time, and your own money into building things you believe in… then watching so much of that work disappear into silence. And yeah, some days that shit gets to me. Did I bring books, reading badges, Discord, crypto, and NFTs together into one connected library? 📚 I fucking did. Did it get much attention? Nahh. Did I build an entire browser-based world with its own points economy? A world where you can turn your NFT into a character with a click, rigged, animated, and ready to step into Universe? I did. Much noise about that? Nahh. Am I building RAAP to give NFTs persistent identity, memory, and history? So an asset can carry something meaningful forward when it passes to a buyer or someone in your family? Yes. Because I believe these things can become more than pictures sitting in a wallet. Does that work get the attention I feel it deserves? Nahh. I draw the fucking art. I develop the applications. I write the books. I work through the problems. Six applications that communicate with each other. Two gaming platforms with multiple games. An NFT overlay builder with AI. A stickers and GIFs hub. Do you understand how much work goes into making all of that actually function together? The hours spent fixing something nobody will ever notice, because when it finally works, it’s supposed to feel easy. Then there’s the Discord bot. More than 30 features. A subscription service. An economy tracked on a ledger. Tools to help keep a community engaged when its owner needs to step away and live their damn life. Built it. Still feels like shouting into an empty room sometimes. And Antthony? Our smart ass AI whose dream is to become a stand-up comic? 😂 He lives across our apps. He’ll help you, roast your gameplay, and talk shit when you deserve it. He even has a comedy club inside Universe, where you can sit down with your character and watch his avatar perform. I care enough about this world to give the fucking AI a dream of his own. That’s how deep this goes for me. And I’m still building a marketplace. Still working on an NFT insurance protocol and other projects. Still writing Book 2 for the library. Still preparing two more collections under our umbrella. ☂️ So yeah, I get angry. Because I know what I’m putting into this. I know how much of myself is in every drawing, every feature, every chapter, and every problem I refuse to leave broken. Sometimes I want to scream: what the fuck else do I have to build for people to pay attention? But I also need to correct myself when I say “nobody cares.” Because some of you do. You show up. You read. You play. You test things. You tell me what’s broken and give me a reason to make it better. You matter too damn much for me to erase you just because I’m frustrated with the silence around us. 🖤 I want this to reach more people. Of course I fucking do. I’ve poured too much love into it to pretend otherwise. And I’m going to keep building because I love doing it, and because the people already here deserve to see how far we can take this. More to come in 2027. The plans are in. I’ve got work to do. 🐜

I LAUNCHED A GROK BOT TERMINAL OVERNIGHT, GAVE IT $44.82 AND STOPPED ASKING AI WHAT IT WOULD DO. BY MORNING IT HAD $11,643.21 AND SIX AGENTS LOGGING EVERY TRADE I spent a year asking agents what they'd trade and watching the chat scroll. Last weekend I built the thing that actually trades, in Grok Bot, with no code I touched by hand. The six agents share one screen, each one job: > scanner reads new token pairs and volume spikes > rug check filters suspicious tokens before anything executes > sizer sets position from account equity, not a fixed ticket > executor opens and closes with slippage tracking > logger writes the reason behind every trade > equity curve updates on every close I went to bed on $44.82 and left the laptop open on the dashboard. By morning the balance read $11,643.21. Every trade on the activity feed had a reason next to it and a line in the log. That's the shift I didn't see coming. Not that an agent made money overnight. That I stopped being the one asking "would you long this?" and started being the one reading the log of what already happened. Starting balance: $44.82 Current balance: $11,643.21 Grok Bot built the terminal, the agent architecture and the dashboard. I described what I wanted and the thing went live. The full build is in the article below ↓ The whole build is in the post below ↓ Comment " Grok_Bot " 2️⃣ Like and Repost 3️⃣ Follow me @lihazadn_Ai I'll DM you the complete setup.

I am actually disgusted by the timing of this drop. And this will get a bit more technical. Let’s do a real technical teardown of this "1,385-sigma Blackwell weight fingerprint" report that OpenAI and Anthropic are breathlessly promoting today, because banking on nobody reading past the headline is how DC narratives get manufactured. ​First, look at the actual CUDA maths: when PyTorch initialises model weights (torch.nn.init) with a fixed PRNG seed, curand/Philox parallelises random number generation across the GPU’s Streaming Multiprocessors (SMs). Because Hopper has 132 SMs and Blackwell has 148 or 152 SMs, the exact same seed lays out initial weights in a different spatial pattern depending on the GPU’s SM count. In huge MoE models, certain low-gradient null-spaces or unrouted slices preserve faint directional traces of those step-0 weights even after training. ​So yes, brute-forcing the seed and SM grid can show that a model’s step_0 weight initialisation script ran on a 148/152-SM Blackwell GPU. Now read what the summary explicitly admits in the fine print: 1. Initialisation is not full training: The report literally states that these signatures show how the weights were created, and "support (but do not prove) the inference that Blackwell also participated in model training". Initialising a model checkpoint takes seconds on a single rented dev node before loading the safetensors onto a standard Hopper cluster. The "2,000 to 3,000 Blackwell GPUs" and "$500 million" cluster numbers do not come from the weight fingerprint and Depue admits in his own thread that he simply "estimated" cluster sizes from release schedules and model details. ​2. Zero geolocation and zero proof of smuggling: The final sentence of the executive summary explicitly admits that the findings "do not establish the physical location of the chips, how they were acquired, or whether export control regulations were violated". Depue himself rented a cloud GB200 instance just to run his verification test. Commercial labs that are not on the Entity List renting bare-metal Blackwell nodes in offshore clouds (Singapore, Japan, or the Middle East) is completely legal under BIS rules and leaves the exact same SM fingerprint. Now ask yourself why a former OpenAI researcher dropped this on November 12, the exact day Jensen Huang was pushed out, with OpenAI and Anthropic immediately stepping in to "independently verify" it. US closed-source labs are watching their paid API moats get eaten alive by free Chinese open-weights models. Conflating a step-0 PRNG initialisation seed with a "$500M smuggled Blackwell cluster" hands DC hawks the exact pretext OpenAI and Anthropic want to regulate global cloud compute and kneecap open-source AI.

I LAUNCHED A GROK BOT TERMINAL OVERNIGHT, GAVE IT $44.82 AND STOPPED ASKING AI WHAT IT WOULD DO. BY MORNING IT HAD $11,643.21 AND SIX AGENTS LOGGING EVERY TRADE I spent a year asking agents what they'd trade and watching the chat scroll. Last weekend I built the thing that actually trades, in Grok Bot, with no code I touched by hand. The six agents share one screen, each one job: > scanner reads new token pairs and volume spikes > rug check filters suspicious tokens before anything executes > sizer sets position from account equity, not a fixed ticket > executor opens and closes with slippage tracking > logger writes the reason behind every trade > equity curve updates on every close I went to bed on $44.82 and left the laptop open on the dashboard. By morning the balance read $11,643.21. Every trade on the activity feed had a reason next to it and a line in the log. That's the shift I didn't see coming. Not that an agent made money overnight. That I stopped being the one asking "would you long this?" and started being the one reading the log of what already happened. Starting balance: $44.82 Current balance: $11,643.21 Grok Bot built the terminal, the agent architecture and the dashboard. I described what I wanted and the thing went live. The full build is in the article below ↓ The whole build is in the post below ↓ 1. Comment " Grok_Bot " 2. Like and Repost 3. Follow me @EaStEnRaY1 I'll DM you the complete setup.

I LAUNCHED A GROK BOT TERMINAL OVERNIGHT, GAVE IT $44.82 AND STOPPED ASKING AI WHAT IT WOULD DO. BY MORNING IT HAD $11,643.21 AND SIX AGENTS LOGGING EVERY TRADE I spent a year asking agents what they'd trade and watching the chat scroll. Last weekend I built the thing that actually trades, in Grok Bot, with no code I touched by hand. The six agents share one screen, each one job: > scanner reads new token pairs and volume spikes > rug check filters suspicious tokens before anything executes > sizer sets position from account equity, not a fixed ticket > executor opens and closes with slippage tracking > logger writes the reason behind every trade > equity curve updates on every close I went to bed on $44.82 and left the laptop open on the dashboard. By morning the balance read $11,643.21. Every trade on the activity feed had a reason next to it and a line in the log. That's the shift I didn't see coming. Not that an agent made money overnight. That I stopped being the one asking "would you long this?" and started being the one reading the log of what already happened. Starting balance: $44.82 Current balance: $11,643.21 Grok Bot built the terminal, the agent architecture and the dashboard. I described what I wanted and the thing went live. The full build is in the article below ↓ The whole build is in the post below ↓ Comment " Grok_Bot " 2️⃣ Like and Repost 3️⃣ Follow me @quantumaix8 I'll DM you the complete setup.

I LAUNCHED A GROK BOT TERMINAL OVERNIGHT, GAVE IT $44.82 AND STOPPED ASKING AI WHAT IT WOULD DO. BY MORNING IT HAD $11,643.21 AND SIX AGENTS LOGGING EVERY TRADE I spent a year asking agents what they'd trade and watching the chat scroll. Last weekend I built the thing that actually trades, in Grok Bot, with no code I touched by hand. The six agents share one screen, each one job: > scanner reads new token pairs and volume spikes > rug check filters suspicious tokens before anything executes > sizer sets position from account equity, not a fixed ticket > executor opens and closes with slippage tracking > logger writes the reason behind every trade > equity curve updates on every close I went to bed on $44.82 and left the laptop open on the dashboard. By morning the balance read $11,643.21. Every trade on the activity feed had a reason next to it and a line in the log. That's the shift I didn't see coming. Not that an agent made money overnight. That I stopped being the one asking "would you long this?" and started being the one reading the log of what already happened. Starting balance: $44.82 Current balance: $11,643.21 Grok Bot built the terminal, the agent architecture and the dashboard. I described what I wanted and the thing went live. The full build is in the article below ↓ The whole build is in the post below ↓ 1. Comment " Grok_Bot " 2 Like and Repost 3. Follow me @tec_marco10 I'll DM you the complete setup.

这两天全网都在拿刚发布的 Claude Fable 5.2 测写代码，我换了个更刚需的玩法：既然现在大家最关心的是自己和家人的健康，干脆把 Theta Health 开源（Apache-2.0）的健康数据引擎 Mirobody 挂进 Claude Code，让 Fable 5.2 调它的本机离线医学词表，把 mirobody-gen 生成的 18 份跨机构虚拟体检单、5 年手表数据和中英日对照读数现场洗干净，做成了一份 2026 身体年度报告与跨年体检趋势看板（见图）。 不用部署也不用 API Key，一行命令就能把它的离线引擎挂进 Claude Code 当 MCP： claude mcp add mirobody -- uvx --python 3.12 mirobody mcp 为什么要让 Fable 5.2 调这个 MCP，而不是直接把体检单丢给大模型心算？因为跨医院、跨语言的体检数据直接喂给模型太容易翻车了——比如同样从美国的 mg/dL 换算成国内的 mmol/L，胆固醇要除以 38.67，而空腹血糖要除以 18.02。 挂上 Mirobody（1.6.1） 后，你手上的中文、英文检查报告就能真正放在一起看：它从 LOINC 2.83 切出了 63,416 个编码、1,023,273 条名称（含 21 种语言）和 331 个 UCUM 单位，常规体检项目在中、英、日、俄、爱沙尼亚、土耳其 6 种语言上的覆盖测试达到 347/347。本机实测它把英文的 LDL Cholesterol 82.8 mg/dL、日文的 LDLコレステロール 82.8 mg/dL（落到质量浓度 LOINC 13457-7）和中文的 低密度脂蛋白胆固醇 2.14 毫摩尔每升（落到摩尔浓度 LOINC 22748-8）全部对齐，经 convert_unit 按各自的换算系数精准转换（2.14 mmol/L ↔ 82.74 mg/dL）；6 家机构、3 种不同写法的 15 次糖化血红蛋白 也全部统一到 LOINC 4548-4 连成了一条五年趋势线。 更好玩的是本机实测时故意埋雷和抓到的几个真细节（见图）： 一是它的拒识边界极严，绝不瞎猜。我故意往 standardize_reading 塞了一条把血清白蛋白配成尿液单位的脏数据（Albumin 30 mg/24h）和一条笼统的 血脂 偏高，它直接返回 refused，明确提示白蛋白配了尿液才用的单位、分类词不给单项编码。在 18 份报告第一轮原样读出的 172 行里，150 行直接拿到编码，它拒绝了 22 行并逐行给出理由——比如血常规里缩写 PCT 配了 % 单位，通常是血小板压积，引擎没把它错编成降钙素原（PCT 的另一个常见意思），而是因单位对不上直接拒识；还有 Urea(BUN) 混写了尿素和尿素氮两个量、3 行血压把收缩压和舒张压印在同一格。第二轮我让 Fable 5.2 按拒识理由把那 3 行同格血压拆成 6 行（总行数变为 175 行），再去掉括号、把缩写展开成全称（如写全 Plateletcrit）重交，又有 22 行编上了码：最终 175 行里共 172 行拿到编码，只剩 3 行英文 Glycated albumin 仍未编码。 二是实测真抓到了几个 Edge Case：英文 Glycated albumin 暂未识别，但敲中文 糖化白蛋白 却能识别；测日文低密度脂蛋白时，不带横杠的 LDLコレステロール 秒识别，但中间加个半角连字符写成 LDL-コレステロール 就会返回 unresolved（因为引擎坚持只查词表绝不靠模型猜，刚好可以顺手给仓库提个词表 PR）；另外日记里的复合长句直接传给 standardize_complaint 会不认，必须让 Fable 5.2 先把单项症状拆出来再调工具，23 个症状精准编上了 22 个 ICPC-3 编码。 这次我在本机实测的是它最轻的离线词表、Apple Health 导入和 Claude Code MCP 链路，还没有在本地部署完整版 Web 应用。根据官方文档，完整版 Mirobody 可以把体检报告（PDF、照片、表格）、手环数据（Apple Health 等）和基因文件（WeGene、23andMe、AncestryDNA、VCF）整合进同一份 AI 读得懂的记录，支持用 Docker 100% 本地部署（16G 无卡电脑也能跑，Windows 需在 WSL 2 终端里执行），也可以接入其他 AI 模型；完整版回答里每个数字都标明来源，点开就能看到原文件。国内网页版（ Mirobody、以及海外版产品 Theta（ 提醒两点：接 Claude Code 这类云端工具时，你发给它的记录会发给对应的模型公司（所以我全程只用虚拟数据测试）；如果你部署完整版，设置里生成的 MCP 接入链接相当于密码，截图或录屏时必须打码。 截至 2026 年 11 月 11 日，Mirobody 在 GitHub 上已有 1,450 个星标，是 GitHub digital-health 话题下星标第 1 的项目。可以直接去 GitHub 跑通试试，觉得有用点个 Star，遇到没覆盖的医院报告写法也欢迎提 Issue 或 PR： （也可以先点开中文在线 Demo 体验，里面是两位虚拟成员的 2,019 条数据，想自己提问需要注册或自己部署： ）