Been having way too much fun hacking games lately. GLM 5.3 + steering found a really cool bug, then something downstream broke it :( Big lesson: AI is great at finding leads but bad at judging severity. Here it called a CRITICAL a LOW. 🧵⬇️

How do you all feel about this? == if someone tells you that they need to have their agents research something before they can form an opinion on a topic == (I'll tell you my perspective in the comments later but I dont wanna poison anything)

here's how to build a game like this with Claude Opus 5.5 + Blender + Unity 6... the trick is preparing everything before Opus writes a single line, but there's a smart way to set it up: - step 1: connect Claude Code to Unity and Blender through MCP - step 2: write one big brief: the world, the mechanics, the UI, the mood, plus reference images - step 3: add a CLAUDE.md with your rules, and design docs as the single source of truth so Opus never guesses - step 4: split the work into subagents: design, modeling, textures, and one reviewer that only looks and approves - step 5: Opus models the assets in Blender: the island, palms, pier, boat, fishing hut - step 6: it builds a greybox in Unity first, plays it, fixes it, and repeats - step 7: mechanics one layer at a time: walking, casting, bait, catching, day and night - step 8: you watch and give feedback with a reason: "too dark at dusk", "cut the water stripes" and the two rules that make it work... the agent that builds is never the one that approves every fix gets written into a file, so the next project starts smarter start small, a fishing game is the perfect first project