Loading post
Loading @canghe's post
@canghe
初心者のタンクにカスの嘘を吹き込むゼニヤッタ
24時間テレビ 歌合戦 23:30〜 有吉ゼミ：工藤阿須加、とにかく明るい安村、もう中学生 有吉の壁：佐藤栞里、チョコレートプラネット、シソンヌ、パンサー 上田と女が吠える夜：大久保佳代子、若槻千夏 世界まる見え！テレビ特捜部：岩田絵里奈 バズリズム02：バカリズム DayDay.：アン
個人的に無料版CatGPT,Claudeでも一発で読み込めるadhx.com使ってるな〜 𝕏.comの先端に三文字追加するだけでいいし… (というかfxtwitter何故か読み込めなかった)
How I combined the best of @poteto's pstack and @kunchenguid's Firstmate into a single runtime. Instead of letting their routers fight as separate authorities, I kept Firstmate as the outer loop for fleet orchestration and injected pstack's engineering discipline directly into the workers runtime. >Firstmate is a fleet commander (horizontal scale across Git worktrees). >pstack is an elite micro-manager (strict engineering habits and verification). Here is how I merged them into an optimized hybrid runtime: * Conditional Briefs: Worker prompts load plays just-in-time. Zero bloated prompt dumps. * Required-Read Habits: Smallest logical change, subtract code before adding, and analyze blast radius. * Context Discipline: Only map how the system is built when the change crosses into another part of it. If you skip that, write one line saying why. * Verification: "Done" requires real artifact proof (running live shell commands or generating local app verifiers). * Scaffold Isolation: Worktree checks prevent role hijack across ship, scout, and supervisor agents. I stripped out the Cursor UI dependencies for my local machine's CLI stack and skipped the expensive multi-frontier review loops. Firstmate handles the fleet isolation. The injected runtime handles the code discipline. The goal is lean, fast and deterministic. Just wired this up today, so I will be seeing how this works on my projects. html artifact- Repo links: pstack: Firstmate:
How to Build a One-Person Media Company With Hermes Bots
You are right to push back
有老项目可以想 redesign 的可以试试这个 skills：redesign-existing-projects 大名鼎鼎的 taste skill 的一部分，专门为 redesign 设计，分为三步：Scan - Diagnose - Fix 我在一个项目上简单用了一下，还是不错的，这几天深入用一下看看效果怎么样。
Pi 现在也能直接用 Claude Pro/Max 订阅了。 pi-anthropic-auth 专门补上 Pi 对 Anthropic OAuth 的兼容缺口。它不是重写 provider，而是在 Pi 原生 Anthropic transport 外加一层薄封装： • 保留原生 /login anthropic • 保留完整模型列表 • API Key 请求和其他 provider 完全不受影响 • 只在检测到 sk-ant-oat OAuth token 时启用 • 交互轮次与 compaction 都能覆盖 安装一行： pi install npm:@gotgenes/pi-anthropic-auth 然后照常执行 /login anthropic 即可。目前项目 181 Stars，最新 release 为 v2.0.6。 注意：Pi 0.80.8 及之后版本中，自己运行独立 agent loop 的后台 Agent 是已知例外，需要按项目文档使用 workaround。 如果你想在 Pi 里复用已有 Claude Pro/Max 订阅，这个扩展值得收藏。
oh my pi, meet oh my fleet. OMP is now supported inside Agent Orchestrator. Give every task its own isolated worktree, run multiple OMP sessions in parallel, and track the code, PRs, CI, and reviews from one live board. your favorite harness just got a control plane. @_can1357 x @aoagents
some of our fan base aren’t real
This is a live demo from the future!!! 🤯🤯🤯 An interactive sitcom? A playable episode? Games and movies are merging into one thing. I genuinely cannot stop playing this. Real-time video generation will change the entertainment industry forever. We are so close. Thanks to @fal team. @Hailuo_AI
Britney Spears - Instagram Post (08/28/2026) - 🕊️🌹🕊️
Them Creamfields vibes
Every time this pops up I have to watch it. Incredible
Anyone want to see a glitch in the matrix?🤯🧐 The ball phased right through the net like it wasn’t even there.
Divorced mom on 1st date- after one glass of wine: “Would you fudge my pie?”
How to build your first team of agents:
How we built our knowledge base
Rainmaker just produced ~19M gallons of water in Alaska via next-gen cloud seeding over 3 hours of operations. We are the first company to provably produce precipitation in Alaska. As promised, we’ve linked our white paper and relevant data. In the future, Rainmaker will protect and restore glaciers with man-made snowfall. Immediately, this demonstration shows how Rainmaker will add new water to the Colorado River and Great Salt Lake in the coming months. We turned around this analysis and white paper just a couple days after operating. There are many data sources I want to deepen our understanding of the atmosphere and increase our provable production; we’re building the instruments to collect that data in subsequent operations. But at Rainmaker, we won’t tout LOIs, simulations, or lab tests. What matters is physically measuring that you’ve affected the atmosphere; proving that we’ve produced water. We prefer sharing only the tech that has proven to make more water for farms, industries, and ecosystems in need. Expect a regular cadence of these from us as we build the best atmospheric science lab in the world. Feedback is welcome in the interim. Rainmaker Century. https://www.rainmaker.com/blog/alaska-validation-report
Jessica Cook is an award winning Artist - here she is in Brooklyn, JYC, presenting her latest piece of ‘Art’. Yes just like everything else - the World of Art is being decimated too.
Vercel just solved the biggest problem with trusting agents to write your code. yesterday they shipped Foreman - an open-source software factory. 58 stars. Nobody's seen it yet. The idea? Instead of one agent writing, reviewing and merging its own work - rubber-stamping its own bugs… Foreman splits the loop into four stations, each one an agent in its own sandbox. And the reviewer runs on a DIFFERENT model vendor: it never sees the implementer's reasoning, only the pushed branch. The agents can't collude. The flow is simple: label an issue "factory" → work enters the line Classifier → triages it, asks questions if it's vague Analyst → turns it into a plan with acceptance criteria Implementer → codes it in a sandbox, runs your repo's own checks Reviewer → judges the branch against the criteria, can send it back twice you → get a draft PR. review, mark ready, merge It also keeps a "factory brain" - durable memory of your repo's quirks that survives across runs. Issue text can't write into it, so nobody prompt-injects your factory. -> MIT. One deploy button. Published by Vercel.
There Are Only 4 Ways to Make Money. Everything Else Is a Story.
Dude nails this cover of "Yellow" by Coldplay https://x.com/punt_rd/status/2088511794524647443/video/1
How Quants Use AI to Build Regime-Adaptive Trading Strategies (Complete Guide)
So what happened on 2/5?
NEW: Anthropic will reportedly launch “Claude Fable” later today — a Mythos-class model. https://polymarket.com/event/claude-mythos-released-on?via=x-afr2
the concept of having to study (which I hate) to get a job (which I hate) in order to live (which I hate)
do you realize how crazy this is... you can literally change ANY situation just by thinking differently bcz NOTHING in your 3d is permanent. the outside world is just a reflection of your past attention and it holds zero power over you unless you keep feeding it your energy. You have complete control over every single thing in your life
If you’re not automating your tests yet… you’re behind 👀
苍何
