(and a small change to how we run these) Hello everyone!! 👋 First, the honest bit. This one is landing later than Monday, and on purpose. Two things got us here. One, a lot more of you are submitting now. If I am going to really sit with every entry and give it a proper look, a weekend is not enough. This round I went through all of them, watched the videos, opened the repos, the full pass. That takes time and I would rather do it right than rush it. Two, I could feel a few of you running hot. Weekly is a sprint, and burnout was starting to creep in for some. So we are moving to bi-weekly. More room to build, more room to breathe, and the time for me to actually review the work the way it deserves. 🎥 Quick word on the videos. They were a step up this round. Some of the animated walkthroughs and live demos were a genuine pleasure to watch, and yes, I weigh them. A clean demo that shows the thing actually working makes a real difference. However I don't want that to ALWAYS be a requirement. Also you will notice the Heavy hitters that you usually see up here are not currently, some posted late and I decided to let the new entries and first timers also have a chance as well! But certainly, check the original post as every submission has something for you to learn from : 💰 Competition 7 ➖➖➖ 🛠️ A FEW THAT STOOD OUT (in no order, and if you didn't make it, it doesn't mean yours wasn't great) The Pipeline Operator — @Jayden Forshee Runs a whole sales pipeline. Paste a lead and it grades it, writes the outreach, and moves the card itself. The live board where you watch cards move on their own, sat right next to a normal chatbot, was one of the clearest ways anyone has shown what an operator actually is. https://github.com/griffainai/studio-pipeline-operator Board: https://pipeline-operator.vercel.app/board

So I listen to English and Hindi music, I didn't like my English and Hindi music being mixed into one playlist, and I wasn't going to do it myself as I have 450+ songs. I asked claude co worker, it connected to my claude in chrome and for 2 hours straight it moved, verified, removed songs from the 2 respective playlists. 0 Manual work and I was claude coding other projects in the back.

Hey guys, quick question. How many of you use separate AI platforms when you are doing deep thinking and deep research? I came across this bias about a year ago. I was doing some research, did a little double-checking, and realized something. Using the same AI for both thinking and research makes the results biased. I kind of attribute it to a student grading their own test. The same brain that wrote the answer is the one deciding if the answer is right. So now I am curious where everyone here lands on this. Are you splitting it across two tools, or running it all in one? And if you run it all in one, have you ever caught it telling you what you wanted to hear?

I wanted to mark this one out loud. @Bas Rosario is the first member who isn't an admin to reach Level 7 in here. He earned every bit of it. If you've spent any time in the forums, you've run into Bas. He's the one greeting new people on the welcome board before anyone else gets there. He's the one leaving real feedback on your work, not a thumbs-up and a move on. And he teaches by meeting you exactly where you are. He's teaching his wife, a cosmetologist with no tech background, to think in systems. He explained ICM to her with a birthday cake. A cake is a system, he said. It has steps. You gather the ingredients, you preheat the oven, and you do them in order. That's what ICM does with the AI. It hands it one step at a time. That's the gift. He can take the thing some of us are still wrestling with and make it small enough to hold. And when you try to hand him the credit, he won't take it. On Saturday's call, the room joked that he's the new authority around here. He shot it down on the spot and pointed at the people he learned it from, naming them one by one. He builds things to route you to the right help, not to put himself at the center of it. He does this constantly. Not in bursts when he wants attention. Every day, in the background, for people who didn't ask and couldn't repay him. That's the whole thing. Level 7 isn't a reward for showing up. It's what showing up for other people looks like after you've done it for this long. And no, he's not a bot. I know the running joke. The steadiness almost makes the case for it, in a room full of people building AI. But that's the tell. Bas has said he shows up here every day on purpose, out of genuine gratitude for what this place has given him. A bot can post every day. It can't be grateful. Bas comes back because he is. That's the most human thing in here. Bas, thank you. This community is better because you're in it. If Bas reviewed your work or helped you when you were stuck, say so below. He should hear it.

Personally. No I don't think they did, I think the researchers are discovering what I did already ! And I'm happy they are. I would love if you all could comment, share or tag Google in this though as I would love to work with them ! Video below. https://cloud.google.com/blog/products/data-analytics/how-the-open-knowledge-format-can-improve-data-sharing