This is one of the best videos I’ve seen about LLMs from the perspective of history and how they work. https://youtu.be/YmLp8qe87A0?is=NAXmkvOCWrlDvOma

https://x.com/viktoroddy/status/2075545587093807111?s=46&t=Ka8CrZvvfpcPZcdnqIqR3w This workflow is incredible and he broke down all of the steps. Lots to learn here.

https://github.com/emilkowalski/skills

I just published WAVES, the method I have been using to run AI agents in parallel without letting them run wild. An agent will always tell you the job is done, and WAVES treats that as a claim and checks the evidence behind it before it counts. You fan the work out to a team of agents, each one owns a slice, and the verifier is what decides when the work is done. It runs in Cursor, Codex, Claude, and Droid, and ships as a skill you can install today. The full breakdown is on the blog, with diagrams, the handoff format, and where it fits next to loops and parallel orchestration: https://www.rayfernando.ai/waves-workers-aggregate-verify-extend Skill: https://github.com/RayFernando1337/rayfernando-skills/tree/main#waves--fan-out-to-parallel-agents Give it a run on something real and tell me how it goes.

You are building a production-quality multiplayer browser game named RF-Zero. Goal: Build a retro SNES-inspired from F-Zero hover racing game that multiple viewers can join and play live from a deployed URL by the end of this session. Requirements: - Next.js + TypeScript (and select the best game engine for this see if you can do three.js) - Real-time multiplayer using SpaceTimeDB - Canvas-based or lightweight game rendering - Lobby or room code - Keyboard controls - Track with laps - Mobile and Desktop playable - Player positions synced in real time - Simple leaderboard - Clear visual polish - Lots of extra JUICE so that players can get power ups and can slow others down similar to the way you can do things with mario kart and other games - Deployable to Vercel Important: Use ref tools and exa code mcp to look up docs. First create an implementation plan. Then build in vertical slices. Prioritize a playable end-to-end version before polish. At every major step, explain what you are doing and why.