Roadster teapawt.net/i/broadcasts/1yKAPwNgg…
0:00
Tesla
Roadster
Louis retweeted
Tesla Wrap Designer by @louis_onchain just joined TrustMRR
💰 Revenue (30d): $1.3k
💵 Total revenue: $3k
📈 Growth (30d): +109%
trustmrr.com/startup/louisv-…
Louis retweeted
I still don’t understand why everyone is not doing this yet. Elon Musk reposted my Grok Bot GUIDE, and using this exact agent setup, I made $13,100 last week alone.
Eight Grok agents on the desk, $200 a month, running a floor that usually costs a crypto fund $500K a year in analyst salaries.
The morning call is at 4am. I am not in it.
1. SEARCH scrapes real-time alpha, dev GitHubs, and unindexed Telegram signals before CT finds them
2. RISK audits contract functions, mint rights, and LP locks, flags honeypots before entry
3. SNIPER places high-speed orders on chain the exact millisecond risk clearance passes
4. WHALE tracks smart money wallets and flags insider accumulation in real time
5. RUG monitors dev wallet activity 24/7 and dumps the entire position if LP is touched
6. EXIT trails stops dynamically, scaling out as liquidity builds
7. SHILL tracks social volume, momentum velocity, and key influencer calls
8. HEAD OF DESK never trades, routes data, checks handoffs, and brings me the one decision that needs a human
142 tokens scanned, 19 qualified setups, 6 executed trades while I was asleep. Net result: +$13,100 after fees and zero bad fills.
Every agent has its own virtual browser, terminal, and local memory in the cloud. The floor stays active with my laptop shut.
The setup is dumber than it looks:
Download Grok Bot and create your Head of Desk.
Give the remaining 7 agents job descriptions like you're briefing new hires.
Run the workflow once on your screen while they watch.
Hook up Telegram and wallet webhooks.
No VPS, no code, no waiting on developers.
A crypto trading floor used to mean 16-hour screen time, paid alpha groups, and constant fatigue. Mine took one evening to set up.
Save this before your next trade. Save GUIDE.
I gave Elon Musk's new Grok Bot an org chart instead of a to-do list, and in one week I stopped being a founder who does the work and became one who assigns it.
eight bots. one org chart. nobody sleeps but me. here's the whole design, steal it.
step 1 → 0:01 What we're covering
step 2 → 2:01 Installation & Setup
step 3 → 3:14 Building the First Bot
step 4 → 8:18 Teaching by Screen Recording
step 5 → 14:18 Putting it All Together
THE ROSTER:
Atlas, chief of staff. the only bot I talk to. I give it outcomes, never tasks. it decomposes them and delegates to the team in group chat, and it never does specialist work itself. it posts the plan every morning and what shipped every night, and it only comes to me when a decision is irreversible or spends money.
Scout, research. finds and qualifies my ICP. every day: 25 verified prospects, one line on why they need us right now, and a source. if it can't verify, it marks it unverified. it never guesses.
Quill, content. turns what the company learned this week into 5 posts and 1 long piece, in my voice, matched from the last 50 things I wrote. drafts only, it never publishes.
Pitch, outbound. writes a first touch and two follow-ups for everyone Scout marks ready. 60 words max, one specific observation about their business, one clear ask. queued in drafts, I approve in bulk.
Vault, inbox and ops. triages everything into needs-me, needs-a-bot, needs-nothing. it handles the last, routes the middle, and gives me five bullets on the first by 9am.
Ledger, analyst. one report a night: what moved, what didn't, and the single number I should care about tomorrow. no dashboards, no adjectives.
HOW THEY'RE WIRED
one group chat per outcome, not per person. Atlas sits in all of them. the bots hand off inside the chat, so I only read the handoff, I never manage it.
two rules that made this actually work:
1. every charter ends with a hard "never do this without asking" line. autonomy without a fence is just chaos on a schedule.
2. show once, don't describe. I ran the full workflow on my screen one time. that single demo taught them more than a page of instructions ever could.
WEEK ONE
214 verified prospects delivered. 89 personalized outreaches queued and approved. inbox at zero every morning. 11 content pieces ready.
THE POINT
most people are still treating Grok Bot like a smarter chat window. it isn't. it's the first time one person can own an org chart instead of a to-do list. my bottleneck was never how much I could do, it was how much I could hand off.
bookmark this.
Louis retweeted
用grok bot 运营3个账号,做了6980万曝光,32万赞,31万收藏
晚上看了一下,他的逻辑是:
1. 让gork bot重新包装已经被验证过的素材,并且是已经爆款的素材
2.从选题池了抓新的内容
里面有个小技巧,其实可以用x的高级搜索来筛选高互动性内容
min_faves:500
min_faves:2000
min_faves:5000
一层一层筛+bot生成不同角度的内容+人工选择
我还整理了他的提示词+原帖,放评论区吧
Louis retweeted
Lauren Tan @poteto 是 Cursor 的工程师,之前在 Meta 做 React Compiler,也在 Netflix 做过 tech lead 和工程经理。
她加入 Cursor 只有五个月。第一个月还在熟悉代码库,上个月已经合入了 1000 个 PR。这个月才过去 12 天,她又合入了接近 800 个。
这不是 AI slop code,而是你每天都在使用的 Cursor 的代码。
很多人,包括 Claude Code 的 Boris,都提过自己借助 coding agent 达到了类似的效率。但真正愿意把工作方法完整分享出来的人并不多。Lauren 在这个一小时的视频里,几乎是手把手讲了她怎么走到这一步。
她认为,用 AI coding 最大的问题不是生成代码,而是验证代码。
如果 agent 不能自己运行产品、操作界面、读取 CPU trace 和 heap snapshot、打开模拟器并复现问题,那么最后还是要由你来检查结果。你就是整个流程的 verifier,也是无法并行工作的瓶颈。
Lauren 的做法,是先给 agent 建立完整的验证能力:让它能通过 Chrome DevTools 或模拟器实际操作产品,再用 feature map 告诉它每个功能在哪里、怎么进入。这样即使同事只丢来一张截图,或者一句很模糊的 bug 描述,agent 也能找到对应功能,复现问题并验证修复。
每当她发现 agent 在猜测、漏读代码或走错方向,就把这个失败模式写成一条 skill。然后像测试代码一样测试这些 skill:让多个 sub-agent 分别执行任务,由 coordinator 制定 rubric,再让另一个模型交叉检查评分,反复迭代到结果足够稳定。
现在,她甚至允许 agent 自动合并 PR。有一天早上醒来,已经有 20 个 PR 自动进入 main;她直接在 main 上检查,结果都没有问题。
这套方法不是简单的提示词技巧,更像做工程管理:先设计好环境、流程和验收机制,再让团队并行工作。只不过这支团队,现在由几十个 coding agent 组成。
Louis retweeted
this is fun!! for comparison I asked Fable to make it with three.js and transformers.js and onnx Depth Anything, but it's not near TypeGPU performance. I've got to learn it now
demo: radames.github.io/relight-th…
code: github.com/radames/relight-t…
Thank you all for the kind words under the demo I posted :D
The demo is now officially public and open source for you to play with, modify and build on top of. Feel free to tag me if you make something cool with it :)
Also thank you @iwoplaza for participating in my silly video haha
You can run it like any other TypeGPU example here:
typegpu.com/examples/#exampl…
The source code lives in the TypeGPU monorepo:
github.com/software-mansion/…
The repacked weights used by the example live here:
huggingface.co/reczkok/depth…
今晚别刷Netflix了。
去看这个斯坦福2小时34分钟的讲座。
这是我见过最清晰、端到端讲透ChatGPT和Claude到底怎么建出来的课。
从Tokenization和BPE开始,一路到Transformer架构、训练管线、Next-token解码。
不管你是从没写过一行AI代码,还是天天在ship Agent,看完都会把很多“原来如此”的点一次打通。
真正核心就这几层:
1文本怎么变成模型能吃的数字(BPE tokenization)
2语言模型本质就是在预测下一个token
3Transformer怎么用Attention做消息传递
4训练时用NLL loss把整条序列概率拉高
5生成时怎么一步步解码出来
大多数人花好几年才拼出的全景图,这节课直接给你画完。
把时间空出来,这可能是你这个月最值的一堂课。
Louis retweeted
最近我们持续把这两年SEO 实战中反复验证的流程整理成可复用的 Codex Skills,逐步开源。
这次开放的是 Backlink Skills,这个项目带着700+我们已经提交过的免费外链地址信息,支持通过codex驱动自动化提交skill,让提交外链的人工工作量大幅降低,欢迎大家参考和star: github.com/flaqai/backlink_s…
🤖 Made with AI
最近做了一个新的 Logo Skill,效果挺不错的:
github.com/s1dashu/ip-as-log…
背景是:最近发现 grok bot, coze, workbuddy, 豆包, kiro 等等产品,其实都是在将产品 IP 形象直接作为产品的 Logo,Logo 辨识度极高,同时增强 IP 记忆,感觉挺不错的。
所以最近我的所有产品 logo 都有一个对应的可爱小 IP,并且直接使用 IP 作为 Logo,Vibe 的产品多了,逐渐就形成了这个Skill。
这个 skill 的核心:
1. Logo First,IP Second:首先保证它是一个简洁、清晰、易识别的 Logo,其次才是一个可爱的 IP 形象,避免复杂插画感。
2. 极简构成:只保留最有辨识度的轮廓与五官,用尽可能少的形状完成设计,缩小后依然清楚。
3. 圆润、浑厚的线条:避免尖角、细线和锐利结构,让形象更加友好、稳定,也更适合作为 App Icon。
4. Flat-first 超轻拟物:整体仍以平面设计为主,只加入非常微妙的阴影、压痕和明暗层次,增强质感,但不会变成厚重的 3D 图标。
5. 克制的色彩系统:支持单色或双色 IP;通常 IP 内不超过两种颜色,加上纯色背景,整张 Logo 最多控制在三种主色以内。
6. 高占比人格化构图:IP 从左下角或右下角探出,占据较大的画面比例;通过简单的眼睛、嘴巴和姿态建立性格与记忆点。
一句话概括:把一个可爱的小 IP,压缩成一个精致的产品 Logo。
Louis retweeted
I gave this video to gpt 5.6 Sol, asked it create a diffraction grating shader in @threejs. It took quite a few rounds but here it is
Louis retweeted
This carousel's only half done and i'm already too attached to open-source it 😅
was fully planning to share it. now i'm second-guessing myself.
Louis retweeted
I've updated my Stylized Components page with this lovely carousel.
I'm also working on the new Painterly Effect video now that I've finished the scene.
The effect will be free, and for those who want the complete scene, it's available on my Patreon.
stylized-demos.vercel.app/
Louis retweeted
styles.refero.design - High-quality DESIGN .md examples for AI agents
vibeindex.dev - Directory of tools for vibe coders
ui.aceternity.com - React component library for beautiful landing pages
animejs.com - Open-source all-in-one JavaScript animations
minimal.gallery - Web design inspiration
Louis retweeted
发现一个 Logo 宝库:号称世界上最大的标志书
以后做产品 Logo,可以先来这里研究真实品牌的结构、比例和变化,再让 AI 在参考系上二创
AI 负责发散,人先把审美和方向找对
logo-archive.org
Louis retweeted
I turned my @rive_app animation into a real app in about 10 minutes. Without writing code.
Well, Cursor wrote it. I just told it what to do, and it ran on a simulator with live weather data.
Sounds complicated. It's not 👇:
youtu.be/kVaWSQIo0ok
#Rive #NoCode @cursor_ai
Louis retweeted
A hero carousel of portraits, a scatter of album tiles, an icon row, all animating through on scroll. A marketing site with rhythm. by @immad_jilani
Check More now on movin.design
Louis retweeted
What if the border became the animation? 🌈
Nova Glow Navigation features a seamless traveling gradient, smooth text flips, and a responsive mobile experiencenin @framer.


























