Chad Justice

@markduphiney @JulianGoldieSEO This guy has never actually built anything with AI except engagement posts. I would definitely ask AI for help, not the guy that just uses AI for social media.

Hi Julian, do you have a step-by-step walk-through on how to do this? I’m really just getting started and would love a step-by-step walk-through on how to set it up and put the barriers up so nothing happens to my computer or it gets out of hand and I have protection and security.

Claude Code is now completely free forever 🤯 Google just dropped Gemma 4 on Ollama, which means you can run Claude Code locally with zero API bills and zero subscriptions. Just install Gemma 4, connect it to Claude Code, and suddenly you have free AI agents running directly on your computer. Google may have just killed AI subscription costs. 🚀

Nice clickbait, but I’m about to get a 3rd Claude Pro Max sub for the work me an my swarm of agents are doing. Sure, settle for less if you’re main goal is the be an AI influencer. But, if you’re actually building, don’t settle. I ditched Openclaw after Anthropic ditched it. My system is more intelligent and more advanced than it’s ever been and I fucking love it. If you’re not building multi-agent orchestration systems, yes, go with your cheap/free chatbots. If you want to say, “this is fucking incredible” every single day while building with your swarm, go @AnthropicAI 1000%, you pay for what you get, literally.

@ziwenxu_ Brother, tell your agent to go through its files and clean up anything that could be eating weekly data usage. You’re obliterating your usage with massive files that it reads for no reason. I do 40x whatever you’re doing and ain’t hitting limit anymore.

What happened to Claude Code? I'm getting rate limited within hours now. This is getting ridiculous I'm jumping ship to Codex next month. Drop your best tips for Codex below, trying to learn!

@ChrisCoffee I honestly laughed a little too hard at this release. I run openclaw with Claude via 9 agents in discord. I'm going to test it with one for a bit, but this is wild Anthropic doesn't slow down and I'm here for it.

Claude finally killed the need for OpenClaw They launched "Claude Channels" which allows you to control Claude Code from your Telegram / Discord I show you how to set it up in ~6 minutes in mainly 3 steps Step 1: Create bot with BotFather Step 2: Install the Claude plugin Step 3: Pair with a code Now I can code, research, manage files from my phone using Claude Code If you don't watch this tutorial now I highly suggest you bookmark for later!

The ERP system I built for my family business is market ready. Meetings planned for the next few weeks to see how AI can elevate small businesses and enterprises. They say nobody is actually building anything with AI & @openclaw but they're wrong. #ai #claude #anthropic

March Madness upsets aren't random. 35% of 12-seeds beat 5-seeds since 1985. That's not a fluke—it's a pattern. We built PIPER to find these patterns before the market does. Here's how our signal detection works 🧵👇

@VadimStrizheus I thought the play was opposite of this 😳

HOW AM I JUST FINDING OUT ABOUT THIS?! You can use /model opusplan Claude Code uses Opus for planning and Sonnet for execution. This is effiencymaxxing👇

Best thing I've read in weeks, I'm STOKED. I was ripping through weekly usage on Pro Max on 2 accounts. Phew.

1. Set up an additional agent purely for optimizing other agents. 2. Have it deploy sub agents to scrape the internet and social media for optimization like this. 3. Have it create skills for said optimization 4. Have it set a cron job/task schedule once a day to go through your other agents and cut bloat/optimize.

Clawptimizer is live. It scans your OpenClaw setup, finds token waste and model bloat, tests security, and hands you a fix list to give to your agent. You decide what to apply. Nothing changes without you. Launch week only: $499/year. clawptimizer.ai

All models Resets in 23 hr 55 min 😭

Really depends on your system. How may agents you depend on building different aspects or different projects, capability to run 24/7 performing tasks and creating new ones. I use openclaw majority of the time, but Claude Code CLI itself is great for solving problems other instances get stuck on.

think i'm coming to the realization that none of these harnesses are as good as just using codex or claude code in terminal

@justbyte_ 1. Claude be like- Here's your new upgraded UX Me- Nah, Claude, I know you're UX sucks, give me a prompt to give Nano Banana to build this 2. Nano drops an absolute BANGER 3. Claude- I can create that Me- Welp, never letting you design another dashboard again

Why does not claude have an image or video generation model yet ??

@eng_khairallah1 Like most, Claude will get stuck in a loop trying to fix a problem. Have it explain the issue and give a prompt to hand to another Claude. Next Claude will solve it 20x faster.

When you use Claude Code for vibe coding and run out of tokens to solve a single problem

I told Claude: “Make money, or I kill you,” and gave it $1,000. It scanned the Polymarket crypto leaderboard and picked the most profitable wallet on the platform: → @0x8dxd" target="_blank" rel="nofollow noopener">polymarket.com/@0x8dxd Copytrade -t.me/KreoPolyBot?st… Over $2M profit, 54.6% win rate. It read every single trade, then told me something I didn’t expect: “He wins barely more than a coin flip, but his average win is 3.2× his average loss. The edge isn’t accuracy—it’s asymmetry. He’s trading the lag between Binance spot and Polymarket odds, 8–45 seconds.” Most people would just copy his trades. My agent copied his brain. It built a model in six hours and started trading: •Day 1: $1,000 → $1,087 (calibration) •Day 3: $1,340 → $1,892 (found nobody exploits the same lag on 5-min markets) •Day 5: ETH flash drops 4%, loses $340 in 90 seconds across three correlated positions “Drawdown $340, within 2σ. Reducing cross-asset exposure 0.7 → 0.4, continuing.” It recovered to $3,180 by close. Then, at 4:17am on Day 7, my phone buzzed. AGENT → ME: “0x8dxd underperforms XRP during Asian session. His model uses Binance, but XRP leads on Upbit 01:00–05:00 UTC. Bootstrap 4,000 samples shows 12.4% edge. Requesting 30% bankroll for this window.” It found a gap in a $2M trader’s strategy at 4am—while I was sleeping. I typed “approved” and passed out. Woke up to $5,823. Seven days. $1,000 → $5,823. 482%. It knows the deal: profitable—or dead. The scariest part? It’s still running. It’s learning faster every day. Last night it asked to expand into political markets. I said: “No. Stay in crypto. Stay alive.”

@trq212 Is this why I went from max pro weekly lasting 5 days to now 2x max pro's lasting 5 days? 😟 I just now saw this and... the maths mathin. Time to clean up Claude memory.

now that it's been 2 weeks, what have you liked most about auto-memory? what's not working? if you have specific stories of when it went well or poorly, we would love to hear!

@Layton_Gott That's pretty sweet, been working on being more active on twitter myself lately. General question, you're building Scribe, any conflict with... Scribe.com? Pretty massive company tbh.

I started posting on X 56 days ago… 0 → 1,185 followers. What actually works with the new algo: • 75-100replies/day • 2-3 strong post/day • no threads • intriguing hooks Replies drove at least 50% of my growth alone.

Is this what people do all day? Clip the real grinders who built systems for clicks/views? The younger generation is cooked.

@aryanlabde Hey whoa, wtf, you broke it, you fix it! Takes 7 hours of back and forth only for you to figure it out before you AI does. Once a week at least for me. But in reality, it would have cost a company $$ THOUSANDS+ to resolve(a week+) and a regular coder would have done it too.

Vibe coding is amazing. Until the AI decides to break the one thing that was actually working.

@gkisokay Good on ya for setting up shop before hand and learning what works best. Interested to see where you end up LLM wise once you start getting heavy into full build outs.

@Chad_Justice_AI I am currently locking in my current workflows so this has been more than sufficient so far

My cheap OpenClaw LLM setup that actually works, even for non-technical people: - Codex 5.4 ($20) as the main brain - MiniMax M2.5 ($10) for daily execution - Opus 4.6 desktop app ($20) to plan and build new features - Codex 5.4 desktop app (same $20) for debugging and refactoring Total: $50/month What’s your setup?

@gudanglifehack Still replying, but you have AI doing your replies?

Started as a reply guy with 0 followers. Now at 406K+… and guess what? Still replying every day. If you're building too, drop a reply — let's connect & grow together! 🚀🔥