Ray
486 posts




an @xmtp_ powered marketplace running on KidBlocksOS KidBlocksOS is an operating system where kids build html5 apps by talking to @openclaw indirectly. games, stories, music, art, science projects generated from voice or text. building is only half of it. the other half is selling what you make. no servers. no app stores. no apis. just @xmtp_ and USDC on @base. wallet setup: 🟩parent completes guided setup on first boot 🟩wallet created directly on the device 🟩wallet holds USDC and signs messages marketplace access: 🟩one global xmtp group acts as the marketplace 🟩new devices request access automatically 🟩approval happens in the background 🟩no accounts, no forms, no email listings: 🟩kid selects an app and sets a price 🟩full html5 app and metadata broadcast to the group 🟩every device renders listings locally 🟩the message history is the database 🟩removing a listing is just another message purchases (automated): 🟩buyer signals intent to purchase 🟩seller responds with payment details 🟩buyer sends usdc directly on base 🟩seller verifies payment 🟩app file is delivered through messaging 🟩small platform fee is sent after settlement everything is a message. listings, negotiations, confirmations, delivery, the app itself. @xmtp_ is the coordination layer. @base handles settlement. this is for crypto native households who want their kids learning entrepreneurship by doing. build something. price it. sell it. receive USDC. learn ownership and peer to peer commerce in real time. @coinbase @ShaneMac @0xDeployer


We are doubling down on agentic first technology Today we are releasing the largest 7 self-improving @clawpumptech Solana DeFi & Social Skills upgrade The full financial stack your AI agent needs to operate autonomously on Solana is here We are the agentic gateway to @solana

level designer AI is easily a $100M opportunity waiting to be unlocked there is so much depth in designing game worlds, even a 3D blockout designer ai would be printing money like crazy some thoughts about what agents should be good at: 1. Clear Strategic Progression AI that helps in building the core experience loops as well as the big loop of intro > buildup > climax > resolution 2. Spatial Design Generating or at least reviewing shapes, landmarks, lighting, colors and cues for coherence and clarity. 3. Pacing Create series of high intensity moments with breaks of relaxation 4. Reward Generate meaningful challenges which feel rewarding. The challenge, depending on the progression in the game, should be just difficult enough for players to feel like they're much more skilled after achieving it. Progression should incorporate new skills after they're unlocked 5. Show, not tell AI should be capable of constructing scenes where the objective is clear from the design of the level using all of the above, without relying on verbose explanations. Current LLMs are very bad at these skills when tasked to create games. They are highly finetuned to mimic known gameplay mechanics. It's not clear to me how this can be done as all points are very tightly coupled to gameplay, so it needs to be able to own and understand the mechanics to be able to build out levels and tell a story. I still think this is very much possible to solve, it needs the right benchmarks for ai agents to train on and open minded experts in these fields to use them and find limitations














