Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

A developer who says he's not a game dev built Riposte, a browser FPS, with Claude Code and three.js in about a month. → Weapons, characters and maps are all generated in code → No Blender, no imported models → Physics on props, cloth and water → Built to...

57,336 Aufrufe • vor 12 Tagen •via X (Twitter)

6 Kommentare

Profilbild von Prajs
Prajsvor 12 Tagen

What's the mobile frame rate?

Profilbild von BlockDown Festival
BlockDown Festivalvor 12 Tagen

Next level!

Profilbild von Evening Trader Group
Evening Trader Groupvor 12 Tagen

Everything generated in code is the wild part, no asset pipeline at all.

Profilbild von Satoshi Drops 🪂
Satoshi Drops 🪂vor 12 Tagen

That "no Blender, no imported models" line is the real flex. If Claude Code + three.js can ship weapons, cloth and water physics in a month, the bottleneck for indie games just moved from art pipelines to prompt discipline. Curious whether @AnthropicAI / @ClaudeDevs see game prototypes showing up more in their usage mix.

Profilbild von Mohammad Vazin
Mohammad Vazinvor 12 Tagen

Code-only assets are the real unlock here. No Blender export, re-import, fix-the-scale loop. When every weapon and map is a function, changing the whole art style is one diff and a reload. Curious how big the build gets once the procedural generators pile up.

Profilbild von 山海MS
山海MSvor 12 Tagen

AI begins to change the game industry, unless it has its own brand IP.

Ähnliche Videos

Claude Code tip, and it's absolute free f*cking gold: run Opus 5.5, Sonnet 5.5 and Fable 5.1 as one team and stop burning Opus tokens on routine work the setup in one line: plan on high, delegate on medium, keep Fable on call • who does what > Opus 5.5 on high - plans and ships the code > Sonnet 5.5 on medium - explorer reads code, worker edits and runs tests, researcher pulls docs > Fable 5.1 via /advisor fable - reads the whole session and speaks up only when it matters • when Fable 5.1 steps in -> before a plan: is this the right approach? -> when an error repeats: am I digging in the wrong place? -> before "done": what did I miss? Jev engineering takes it one layer lower: which file, which tool, retry or stop all go to Jev in under half a second, so the big models only see the real forks paste this into Claude Code ↓ "Rebuild my Claude Code setup: 1. Find subagents in ~/.claude/agents and .claude/agents that fit explorer, worker and researcher. Draft only the missing ones. Set each to model: sonnet, effort: medium. List any that pin a different model and leave them 2. In ~/.claude/settings.json set effortLevel to high and advisorModel to fable. 3. Report anything that disables the advisor (CLAUDE_CODE_DISABLE_ADVISOR_TOOL, DISABLE_TELEMETRY, flag-fetching blockers) and CLAUDE_CODE_EFFORT_LEVEL. Change nothing. 4. Add to ~/.claude/CLAUDE.md: consult the advisor before a large plan, when an error repeats, and before calling a long task done. Show every change as a diff. No edits until I say go." ↳

Mr. Buzzoni

144,764 Aufrufe • vor 29 Tagen