Pinned
7d •
🚀 New Video: Jev + Opus 5.5 Just Killed AI Slop. Here's Proof
If you've been getting AI slop in your outputs, pairing Opus 5.5 with Jev eliminates it. Opus 5.5 is Anthropic's newest model and it writes a lot better. Jev can't write a single word — it only checks. One writes, the other checks everything before it goes out. I ran three weeks of my own AI news through it: 1,300+ stories in, about 200 out. - Two kinds of slop, two doors. Slop with nothing in it (nothing specific, nothing new, or it just wants a DM/click/sale) can't be fixed — you throw it out. Slop that sounds like a machine can be completely true and still read like filler — that one you rewrite. The first kind comes in with what your AI reads; the second goes out with what your AI writes. Jev stands at both doors. - Why Jev and not just a big model. Jev never writes — you give it text and a question, and the only answers allowed are the ones you wrote down, each with a confidence number. Under a second per item, ~4¢ per million tokens in, answers free. At that price you stop sampling and check every item. A frontier model costs 100x+ more per check — at 1,000 items a day that's $400–700/mo versus about $2.50. Small judge on everything, big model only on what it's unsure about. (Anthropic's own docs say the same: lightweight model in front as a screen.) - The rule that makes it work. The writer never grades its own work. A prompt with ten writing rules just hopes all ten land; checking each rule on its own tells you which one missed. If a check fails, the draft goes back to Opus with only the failed checks as feedback — two rewrites max, then it posts the link with no write-up. A bad write-up never posts. My take: this isn't about news. AI made writing almost free but it didn't make reading free — a Stanford study found 4 in 10 office workers got AI work in one month that looked finished and said nothing, ~2 hours each to deal with. Same gate works on customer replies, sales emails, or anything before you publish. The only thing that changes per box is what happens when the checker is down: a news feed can fail open, a customer reply fails closed.
Pinned
Jun 6 •
What do you actually get if you upgrade to AI Accelerator+?
What do you actually get if you upgrade to AI Accelerator+? Some of you have never heard of AI Accelerator+. Others have, but the part that trips you up is the actual difference between this free group and the paid one. Either way, this post will give you clarity. ───The Free Group─── This free group is a bundle of quick resources pulled from my YouTube videos, plus a massive open community that anyone can join. We’re 19,000+ strong in here. It’s a great place to get your bearings and see what’s possible. But because it’s open to everyone, it can get noisy and overwhelming. There’s no clear path through it. You can get help from other members, but I rarely answer questions in here myself. AI Accelerator+ Is The Opposite AI Accelerator+ is a smaller room of people who are seriously committed to building with AI, automating their work, and either landing paid opportunities or making their own business leaner. Me and my team are in there every single day. Not a moderator. Not a chatbot. Me and the engineers I actually pay to build this stuff. And right now, it’s tiny on purpose. We’re in the founders stage. That means two things: 1. The price is the lowest it will ever be. 2. You get a level of access you literally cannot get once this room fills up. When you’re one of 30 people instead of one of 19,000, I actually see your questions. ─── Here’s What You Get Inside ─── 1. Two live calls every week. 2. One technical office-hours session with my CTO Keshav, where you bring whatever you’re stuck on and we build and solve it live. 3. One general Q&A with me, where you get direct access to ask me anything — strategy, tools, your specific situation. 4. Full training on the stuff that actually matters right now.** 5. Building agentic workflows. 6. Vibe-coding real apps. 7. Using Claude Code, Codex, and the tools serious builders are using today. 8. And we update it constantly. The way you build today has already moved on from where it was six months ago, and the training moves with it.
Pinned
Aug '25 •
Monthly Competition Series! Win Access to our Paid Program
Hey everyone! I'm thrilled to announce something that's going to take our community to the next level - Monthly Competitions starting this month! Here's what's up for grabs for our top performers each month: 🏆 Priority Work Opportunities - Our top contributors will be much more likely to receive work directly from our team. When projects come up, we'll be reaching out to you first! 🎁 FREE Lifetime Access to our paid community "Agents to Scale" - No more subscription fees, you're in for life! How to Win: - Share valuable insights and knowledge - Help other members with their questions - Post your wins and case studies - Engage consistently and spread positive energy - Contribute content that moves our community forward As you can see in the picture attached, at the end of the month the #1 Rank will be the winner and in the future will provide rewards for #2 and #3 as well! (if you have suggestions for what #2 or #3 should receive then suggest it down below) We believe in rewarding the people who make this community amazing. You're not just building your own success - you're helping everyone else level up too. The competition starts NOW, so let's see who's ready to step up and lead the way! 💪 Keep sharing, keep building, keep growing. Our community gets stronger because of each and every one of you. Let's make this month legendary! 🔥 Drop a 🚀 if you're ready to compete! Cheers guys, Nick
7d •
🚀 New Video: I Rebuilt My AI Assistant on Fable 5.1 — And It Runs My Business
I ask it how the ads did and it answers out loud, in the car. It has my email, my calendar, ClickUp, the CRM my leads sit in, and the channel my team talks in — and I rebuilt the whole thing on Fable 5.1 this week. Underneath there's no app, no service and no server: it's Claude Code running headless on my Mac inside a folder of text files. - Why it can do so much. Because it's Claude Code, it inherits everything I'm already signed into — email, calendar, ClickUp, Slack, Drive, call recordings. And the part that actually changed how I use it: it drives my real browser, the one with all my logins. Anything without a proper connection (my ad account, GoHighLevel) it just opens the page and reads it the way I would. Two other doors: hand a job to Codex when it's code, or let it drive the Mac itself after it asks. - The voice loop, and what leaves the machine. Everything runs through Telegram, so the interface is a text or a voice note. Voice arrives → transcribed locally with Whisper (no key, nothing uploaded) → Claude Code answers → ElevenLabs speaks it → back as a voice note. No webhook, no server, no public address pointing at my house — my Mac just asks Telegram every few seconds if anything's new. Two things leave: the message, and the sentence to speak. My recordings never do. - Where Fable actually earns it. Not everywhere, on purpose. "What's my next meeting" is one calendar lookup — running that on the biggest brain is taking a helicopter to the corner store. So it picks a model per message: plain lookups to Sonnet, ordinary work to Opus, the genuinely hard ones to Fable. Hard means holding five or six tool results in its head at once and coming out with an opinion. And Fable built the thing too — when the browser timed out, it found the cause and swapped the library; when a tool got quietly blocked, it audited the log and found four more I hadn't noticed. My take: it's a butler, not a specialist. Ask it to write a LinkedIn post and it hands you the brief rather than writing it badly — something mediocre at everything is worse than something that knows what it isn't. It's also not fast (30 seconds to a minute and a half), and it lives on my Mac, so Mac asleep, Jarvis asleep. On the $200 Max plan it costs nothing extra; the dollar figure it prints is an API estimate, not a bill.
10h •
Looking for a US-based Collaboration Opportunity
Hello, This is Fusao, and I hope you're doing well. I'm a Senior Software and AI developer, and I build cutting-edge software systems, intelligent automation, and modern digital platforms. My development projects have been progressing well, and I've started generating a steady income. I'm expanding my operations and looking for a reliable US-based collaborator to support my work and generate more income together. If you're less technical, it won't matter. The role I have in mind is more straightforward and focused on growing together. I hope there may be a great opportunity for us to build something profitable. If you're based in the US and would like to proceed with me, please contact me so that we can discuss this in more detail. Thank you for your time. Best regards, Fusao WA: +1 (774) 733-4233 TG: @moonlight772
1
0
1-30 of 5,335
skool.com/systems-to-scale-9517
A community for mastering AI, Agents, and Automation.
Join today for immediate value!
Leaderboard (30-day)
1
+14
2
+14
3
+12
4
+10
5
+10
Powered by