Focus on the journey stop chasing the destination & buy 3. Crypto class of 2017. AI, Web3, Bitcoin, Ordinals: “whoever has the most bots wins” - Shawnff
The Bot Log | Update 01
After a couple weeks of research, I finally caved and bought a Mac Mini. 🖥️ Arrives Wednesday. It’s officially time to get my first bots online and see what I can build. Currently watching videos on potential workarounds for OpenClaw's bad memory... 🤖 #MacMini #Automation #BuildInPublic
The world’s first @nvidia Vera Rubin NVL72 server rack is here.
We’re thrilled to deliver the first working, liquid-cooled @Dell PowerEdge XE9812 for @CoreWeave.
Built for the next era of AI infrastructure. 🚀🤝
> you open Claude Code.
> you type a prompt.
> it thinks for 3 seconds and gives you an answer.
> you didn't know you could type "ultrathink" to make it actually think.
> you didn't know "/btw" asks a question with zero context cost.
> you didn't know two Claude sessions produce better code than one.
> you've been using 10% of the tool.
> here's the other 90%.
Anthropic accidentally leaked their entire source code yesterday. What happened next is one of the most insane stories in tech history.
> Anthropic pushed a software update for Claude Code at 4AM.
> A debugging file was accidentally bundled inside it.
> That file contained 512,000 lines of their proprietary source code.
> A researcher named Chaofan Shou spotted it within minutes and posted the download link on X.
> 21 million people have seen the thread.
> The entire codebase was downloaded, copied and mirrored across GitHub before Anthropic's team had even woken up.
> Anthropic pulled the package and started firing DMCA takedowns at every repo hosting it.
> That's when a Korean developer named Sigrid Jin woke up at 4AM to his phone blowing up.
> He is the most active Claude Code user in the world with the Wall Street Journal reporting he personally used 25 billion tokens last year.
> His girlfriend was worried he'd get sued just for having the code on his machine.
> So he did what any engineer would do.
> He rewrote the entire thing in Python from scratch before sunrise.
> Called it claw-code and Pushed it to GitHub.
> A Python rewrite is a new creative work. DMCA can't touch it.
> The repo hit 30,000 stars faster than any repository in GitHub history.
> He wasn't satisfied. He started rewriting it again in Rust.
> It now has 49,000 stars and 56,000 forks.
> Someone mirrored the original to a decentralised platform with one message, "will never be taken down."
> The code is now permanent. Anthropic cannot get it back.
Anthropic built a system called Undercover Mode specifically to stop Claude from leaking internal secrets. Then they leaked their own source code themselves. You cannot make this up.
🙌 Andrej Karpathy’s lab has received the first DGX Station GB300 -- a Dell Pro Max with GB300.
💚 We can't wait to see what you’ll create @karpathy!
🔗 https://t.co/8ct5QZ3frS
@DellTech
The Bot Log | Update 08
T-minus 60 hours until the Dell GB10 drops and we give our AI arbitrage swarm real vision capabilities. ⏳
You can’t migrate a messy, bloated agent to heavy enterprise silicon. So tonight we completely rebuilt the Maxbots_Enterprise architecture to cleanly separate Logic from State.
🧠 Right Brain: Persistent Memory & Rules
🛠️ Left Brain: Progressive Disclosure SOPs
Huge credit where it’s due — this clean split came straight from two killer videos:
• @simonscrapes and his “Claude Skills Like the 1%” framework (the exact Left Brain SOP structure we used)
• @openclaw (built by @steipete) and his “OpenClaw Memory Mistake” fix (the Right Brain persistent memory system)
Their blueprints turned a messy swarm into something hardware-ready. The hive is now structured.
Now we wait for the silicon. 👇
The Bot Log | Update 07
Straight grinding and it’s officially live. 🚀
Just shipped V1 of the Maxbots arbitrage engine.
✅ Headless, dual-tier snipers hunting ShopGoodwill & Grailed 24/7
✅ Fully remote-controlled via custom Telegram Command Center (live proof attached 👇)
✅ Ironclad O(1) memory banks — zero spam
✅ Prepped for the live eBay API data pipe
Mac Mini is now running the night shift. Next up: waking up the Dell Pro Max w/ GB10 to spin up local Vision-Language Models for real-time luxury authentication.
We are just getting started.
Resellers & builders — who else is running autonomous arbitrage bots right now? Drop your stack below 👇
#BuildInPublic #Python #AI #Maxbots #Arbitrage #Automation
The Bot Log | Update 06
8 hours of deep work, debugging, and testing... and it's officially live. 🚀
Stripped it down to exactly 122 lines of flawless Python to build a top 1% e-commerce arbitrage engine. It scans, does the math, and flags market anomalies in real-time. Completely autonomous.
I had never coded a single line two weeks ago and here we are talking to Grok & Gemini all night making magic happen.
Time to let the machines work the night shift. 🛠️📈
#buildinpublic #python #automation #ecommerce #arbitrage #reselling
The Bot Log | Update 05
After two weeks of grinding on my very first lines of code, tonight we finally shipped something highly productive: a fully automated local AI pipeline. 🤯
Turned a Mac Mini into a dedicated server for https://t.co/h3JRABOWK3 — my local AI pipeline that turns raw Poshmark flips into auto-generated listings. It takes raw photos via a Telegram bot, natively strips backgrounds, and runs Llama 3.2 Vision locally to auto-generate Poshmark listings.
Phase 1: Automated Listing. (Done ✅)
Phase 2: Building an overnight AI sourcing agent. (Next 🏗️)
We are just getting started. Wait till the Dell Pro Max GB10 arrives next week!
Poshmark resellers — would you run this? Drop your setups below 👇
#Python #LocalLLM #Ollama #BuildInPublic #AIAutomation #Poshmark
This post is a timestamp for the few people still supporting Ordinals against all odds.
If you're one of them:
Drop your Taproot wallet & Retweet this post.
Probably nothing 🟧
The Bot Log | Update 04
Titan is awake. 🔱
Wasn't easy—8-hour battle on a single-node Mac Mini to bootstrap a local, autonomous trading agent (Qwen 2.5 Coder 14B). Hit the walls: safety refusals, VRAM deadlocks, connection timeouts.
Leaned out the stack: slashed context windows, dynamic config patches, swapped polite prompts for raw authority "Hooks." Grind paid off—Titan's sworn its oath to the $500 HITL gate, internalized the rules, and pinged HEARTBEAT_OK.
It's March 7, 2026. World’s on fire.
Tomorrow, Titan hunts Polymarket alpha. 5 days 'til Dell GB10 bare-metal upgrade. The agent economy grind begins.
Who's wrestling local agents on Mac Mini? Drop your hacks below—let's build in public.
#AI #Ollama #OpenClaw #Polymarket #AlphaHunt #AIAgents
The Bot Log | Update 03
Day 4 of the @openclaw_ai saga: 20+ attempts in and I'm still in a standoff with my Mac Mini. 🦞💻
OpenClaw refuses to hatch MaxBot because it insists on having an API key for my local @ollama model.
Running one final "scorched earth" reset tomorrow evening. If it works, the bot wakes up. If not, MaxBot is staying in the digital void until Saturday. #BuildInPublic #LocalAI #DevStruggles
I got thie No API Key found 20+ times…
◇ How do you want to hatch your bot?
│ Hatch in TUI (recommended)
openclaw tui - ws://127.0.0.1:18789 - agent main - session main
session agent:main:main
⚠️ Agent failed before reply: No API key found for provider "ollama". Auth store:
/Users/maxbots/.openclaw/agents/main/agent/auth-profiles.json (agentDir:
/Users/maxbots/.openclaw/agents/main/agent). Configure auth for this agent (openclaw agents add <id>) or copy
auth-profiles.json from the main agentDir.
Logs: openclaw logs --follow