Gret AI

AI maxxing (RIP Solana)

[Zero @zer0point_eth]

Claude Opus 5.5 is completely changing how indie devs build local co-op games

Building local multiplayer used to mean drowning in WebSocket boilerplate just to sync mobile phones as gamepads, until Opus started handling the browser architecture instead

Here is the exact developer pipeline:

→ scaffold a browser-based party game where mobile phones act as native controllers
→ build core multiplayer mechanics like dynamic split-screen views and co-op boss arenas
→ prompt Claude live during your game night to spawn new biomes and expand maps on the fly
→ render your cinematic game trailer and pixel-art assets straight through the model

The real multiplayer development workflow isn't manual netcode setup

It’s a continuous loop:

browser architecture → live testing → mid-game expansion → infinite gameplay

Smartphones as controllers. Zero netcode pain.

[Nenly @Nenlyonis]

用Claude Opus 5.5把我游戏的技能特效系统做了一个几乎可以说是“重做”式的升级。

在开发之初，我的游戏技能特效其实大部分是用社区里开源的一些Shader做出来的。虽然这些Shader在当时帮了我非常多的忙，但后续在基于它们做开发的时候，总是感觉有些束手束脚的——

一方面是因为它本身的代码其实是3D的，但我硬用压缩Y轴的方式模拟了2D俯视角，导致往上方丢的技能范围描述一直很不清晰；
另外就是这些Shader提供的解决方案更像是“套模板”，调节空间其实非常有限，很难构筑出真正符合技能特色和等阶的视觉语言。这就是为啥之前总有朋友会说不同门派和稀有度之间的招式感觉没有什么区分度。

所以这次我干脆让 Opus 5.5 把所有Shader推倒重写，直接按2D俯视角做了一套像素特效语言。简单说说做了啥：

- 刀光、冲击波、气爆、驻留场、飞行体分成几族，每一族有自己的生命周期；
- 发光单独做成一层选择性辉光，只让该亮的东西亮，不靠全屏Bloom糊一层；
- 每个门派制定一套视觉语言预设，再在各种不同形态的招式上提供实现范例；
- 再配套制作了一系列招式编辑器、门派编辑器和特效图鉴，几个变体可以并排摆着比，也能一键进入实机体验。

它让我第一次拥有了我想要的特效：纯正、真实，原汁原味的像素风特效，生动、吸引人的HD光效……并且赋予了我一个高度可控、可延展的VFX系统。

伴随这波改动落地，玩家应该能更清晰地在视觉表现层面品尝到不同门派间的风味特色差异。同时，后期战斗信息的可读性也得到了非常大的改善。

[Gret AI @dogwifblankeh]

@McDonalds Is this real?

[O🌷 @Octoberry]

No wayyy!!

a solo dev with ZERO coding or game development experience built a playable 3D game in just 6 weeks using Opus 5.5 and Godot?

The game combines Ragnarok Online with Monster Hunter, with custom characters, environments, 3D assets, VFX, and shaders.

Opus 5.5 through Claude Code handles most of the development, while Codex helps generate visual references and assets, Tripo AI turns references into 3D models, and Blender handles smaller objects.

The dev even built custom AI workflows to maintain a consistent art style, delegate coding tasks, preserve context between sessions, and verify research.

Budget is around $400/month.

The game is still in development, but the progress is insane tbh

[rewind @rewind02]

one concept art image into a real 3d level with claude opus 5.5 + godot...

opus “churned for 33m 5s”

the trick is scoring the render against the reference instead of eyeballing it, smart way to set it up:

- step 1: pick one reference image as the target look
- step 2: have opus generate the level in code from a seed (rust + godot 4.7)
- step 3: build everything from small pieces: single stones, mixed flagstones, single planks, chains
- step 4: skip textures: stone, wood, brass, cloth and flame are all procedural shaders
- step 5: have opus write a script that compares the render with the reference (color, light, contrast, detail) and gives a 0-100 score
- step 6: fix the scene first: lighting, haze, layout
- step 7: auto-fit a color grade (lut) to the reference as the final step
- step 8: loop: render > score > side-by-side > change one thing

i like this way more than image gen > 3d model > cleanup

one generator instead of 100 assets, and no generation credits burned

[Meticulai @MeticulAi]

How I get Claude Code to actually loop and critique its own game dev work

Almost everything you see went through a build → critique → measure → fix loop.

Here's the setup that made it work. 🧵

#buildinginpublic #indiegamedev #gamedev

[Todd Grilliot @GrilliotTodd]

I said GPT Image 2.5 makes the best spritesheets I've seen from an image model, and I still think so.
It can fail horribly at certain types of animations tho. I think it will be a while before image models really understand good motion. Here's GPT Image 2.5 side by side with the animation model i trained, 12 frames.

[Todd Grilliot @GrilliotTodd]

I had Claude Opus 5.5 animate two of my sprites with code. It's a little scary to me how good it is tbh. It looks like ai is coming for my job after all, and my job IS ai.

Each one cost about $2 on api prices, and 10 minutes of work.
Pixel engine did the same thing cheaper and faster, but dang. I'm certain it will get better. I estimate 6 months to a year before we have claude haiku 7 drawing good pixel art at godlike speeds.

[Haider. @haider1]

this is actually insane

openai deployed thousands of GPT-Rosalind agents to analyze millions of mouse brain cells in 32 minutes, work that could take human researchers months to a year

also the agents uncovered new leads for brain diseases like Alzheimer's and Parkinson's

[Todd Grilliot @GrilliotTodd]

I made this little cute scene for you guys to show how useful pixel engine is getting. 💪💪

Now that you can generate pixel art at any size and animate it, you can do pretty much anything you want. Claude threw this together in a few minutes. All assets generated in pixel engine, including animations

[Loktar 🇺🇸 @loktar00]

Deepseek Flash via Maya. This is the SAME quality I'm getting with the official API at home.

This was done with Deepseek Harness.

In 2024 creating basic shapes with physics using local AI was impressive.

3090s from 2020 running the top 2026 open models is CRAZY.

[Anima @Anima_Labs]

A quick test of AI 3D modeling of my little squire with @MeshyAI !

The tool has really evolved since I last checked!

I have a concept in mind... I need to get better at vibe coding.

[badboyfoxy @badboyfoxy]

Fable 5.5 will be over kill at release if it better than opus 5.5

Opus 5.5 built me this post apocalyptic open word ( not finished yet ) in 17hours

made with Blender and Godot engine this is not final version l

total cost $118 and 17hrs out of my weekly usage

[Gret AI @dogwifblankeh]

@FuentesUpdates Maybe be tell rich b**mers to avoid starting lockdowns and retarded conflicts? Then I might be able to avoid overdraft.

[zero @twoclipping]

Another YT channel made entirely with Opus 5.5 code

assuming an rpm of $5-$10, this guy wouldve already made $12,000 - $23,500

people used to larp YT automation all the time but this is actually real now with opus

[Miko @Mho_23]

this page was created 4 days ago and is already at 170K followers and millions of views from an AI animation story...

if you're not running some type of AI UGC right now you are literally missing out on millions of dollars for your business...

if you still believe AI content doesn't work i don't know what to say anymore. this is by far the highest leverage thing you could be running for your company right now

EVERYTHING is ripping right now:
> DRAMA ads
> AI song ads
> realistic AI UGC
> HTML Animations

this video worked because the storytelling is insane

there's a reason organic native formats like drama ads and animations convert so well.. it's natural content that sits right in people's feeds

AI content is just getting started.. prepare for one of the most insane Q4s we've ever seen

[Orly @orly____]

type shi me n bro do when we zooted

[Max @maxt3chno]

No 3D skills? Just let AI do it in 3 steps

1 - grab a free animation from Sketchfab
2 - generate a custom mesh on Meshy or Tripo
3 - ask Opus / Astra / Argon to swap the meshes

sounds EASY, right? but in reality, it's a TRAP

- mismatched proportions + hands are a nightmare: fix one spiking finger, and another one explodes 3 frames later

- endless iterations: LLMs are blind to cursed geometry, a finger can be bent completely backwards and the AI counts it as "fixed." you have to babysit every single iteration

the final result is passable, but it drained hours of my life and is still far from clean

any recommendations?

[Gret AI @dogwifblankeh]

@yacineMTB total deepseek supremacy