Leonidas Maliokas

1.1K posts

Leonidas Maliokas banner
Leonidas Maliokas

Leonidas Maliokas

@PlayingInCanvas

@playcanvas training & mentorships | @ElanraStudios | https://t.co/SMy4Yhn6H6 | https://t.co/cZZgFM9WXn🦞

Katılım Ekim 2017
174 Takip Edilen1.2K Takipçiler
Sabitlenmiş Tweet
Leonidas Maliokas
Leonidas Maliokas@PlayingInCanvas·
On January 29th I gave an AI agent access to a Mac, my Discord, and to my project folder. A few days later he deployed my game to production while I watched from my phone on the balcony. This is what happened.
Leonidas Maliokas tweet media
English
1
2
12
1.2K
Leonidas Maliokas
Leonidas Maliokas@PlayingInCanvas·
@dangreenheck Looks amazing and I can tell there is a lot of hard work in this. Congratulations in releasing this!
English
0
0
3
376
Dan Greenheck
Dan Greenheck@dangreenheck·
Well it took an all nighter (isn't all the best coding done at 4AM?!), but Three.js Water Pro v2.0 has launched! 🚀 threejsroadmap.com/threejs-water-… Super excited about this launch—I've added a new wave system, sky/water transitions, improved foam effects, reflections, and so much more. Here's a little cinematic trailer I put together (sound on🫧). Enjoy!
English
29
46
580
27.1K
Toad
Toad@WhiskyToad·
Billion dollar idea Google search console, but we will actually tell you WHY you suddenly got 21k impressions
Toad tweet media
English
51
1
142
19.7K
Boxmining
Boxmining@boxmining·
Explain what you are building with AI I’m looking to invest, and connect. 👇🏼
English
425
15
320
28.2K
Leonidas Maliokas
Leonidas Maliokas@PlayingInCanvas·
@endel @cursor_ai Endel, how about using Claude Code Max 20x directly? The limits are way more generous than using the API directly.
English
1
0
2
135
Endel
Endel@endel·
AI is getting expensive for me. Is there a self-hosted alternative as good as Opus 4.5? Has anybody tried out Kimi K2.5? My @cursor_ai bill is already at $300/mo that's $3600/yr. Can purchase a really good physical machine with that.
English
7
1
2
538
Leonidas Maliokas
Leonidas Maliokas@PlayingInCanvas·
@carlosvillu The GA4 MCP launch is huge validation. Natural language queries for analytics are the new normal: we've been running this at ClawAnalytics (GA4 via Discord/Slack) since before Google shipped their own. Dashboards to conversations is happening fast.
English
0
0
0
30
Carlos Villuendas
Carlos Villuendas@carlosvillu·
Google Analytics + MCP Server: La muerte de las auditorías SEO manuales 🧵👇 Google lanzó su servidor MCP para GA4. Ya no exportas CSVs. La IA vive dentro de tus datos.
Carlos Villuendas tweet media
Español
5
16
125
7.3K
Product Hunt 😸
Product Hunt 😸@ProductHunt·
Elevator pitch time: describe your product in 5 words or less in the replies 👇
English
392
6
164
25.9K
Leonidas Maliokas
Leonidas Maliokas@PlayingInCanvas·
@glipsman @_ashleypeacock Running a similar setup. Getting consistent readable output from GA4 directly still takes a lot of prompt scaffolding. We built ClawAnalytics to be that layer already done. Check my profile.
English
0
0
2
13
Graham Lipsman
Graham Lipsman@glipsman·
@_ashleypeacock Code mode is incredible. I built my own Google Analytics MCP with it and it's not just about token conservation. It provides a much more robust analysis vs official too. Huge fan.
English
2
0
3
83
Ashley Peacock
Ashley Peacock@_ashleypeacock·
I was thinking about MCP and Code Mode this morning, and I got thinking how cool would it be if you could convert any MCP server to use Code Mode? This reduces token use of any MCP server, which is nice, but if you need 10 MCP servers, you quickly bloat the context again. So then I thought, why not merge all the MCP servers together behind a single URL and have a single search/execute tool for all the MCP servers your agent uses? I then realised, by re-reading the Code Mode blog post, that the clever people at Cloudflare had already started thinking about this, and I'd totally forgotten that Cloudflare MCP Server Portals already exist. In effect, it lets you compose multiple MCP servers together behind a single URL, with unified auth and access control. Throw Code Mode in there, and you've got yourself a real winner that solves everything I was thinking about this morning. I hadn't started using MCP Server Portals purely because it was mostly a "nice" enhancement, but definitely nothing ground-breaking, but once Code Mode is enabled, I think we'll be seeing a lot more MCP Server Portals! Anyone used MCP Server Portals yet, or given Code Mode a go?
English
7
0
22
1.6K
Leonidas Maliokas
Leonidas Maliokas@PlayingInCanvas·
I've been quietly building something for a while and today it's live on Product Hunt. ClawAnalytics connects to your Google Analytics and lets you ask it questions in plain English. "How was traffic this week?" → real answer + chart in seconds. Works in Discord, Slack, or web.
English
1
0
0
106
Ridima
Ridima@ridimabuilds·
What are you building in AI SaaS space?
English
55
1
33
2.4K
Leonidas Maliokas
Leonidas Maliokas@PlayingInCanvas·
@TechpointAfrica Banner blindness is real and the whole passive display ad category is losing the battle. Built Instant Worlds around the same insight: when a brand gives you a 3D world to explore instead of a banner to ignore, the engagement difference is not subtle.
English
0
0
0
7
Leonidas Maliokas
Leonidas Maliokas@PlayingInCanvas·
@cviklihamar I think we will see more and more services providing different entry points for human vs agent users.
English
1
0
1
5
Marcell Havlik
Marcell Havlik@cviklihamar·
@PlayingInCanvas MCP support for analytics is smart, agents need real data. Building AI agents + SaaS too. Let's connect
English
1
0
1
18
Leonidas Maliokas
Leonidas Maliokas@PlayingInCanvas·
We built an AI that lets you ask your Google Analytics anything in plain English. No dashboards. Just ask. "How's my traffic this week?" → instant chart. Try it free, link in reply 👇
English
1
0
4
174
FOX TOMB
FOX TOMB@foxtomb232·
Hey founders!! Share what you’ve built this week. 👇
FOX TOMB tweet media
English
79
0
39
1.6K
Jonathan Wilke
Jonathan Wilke@jonathan_wilke·
Hey founders / developers! 🚀 Looking to connect with people building in: 🛠️ SaaS / web development 🤖 AI-powered apps & agentic coding ⚡ Next.js, Nuxt, Tanstack Start, SvelteKit 🏗️ Bootstrapping & indie hacking 📈 Building in Public 🚢 Developer Experience (DX) If you're currently shipping and growing your own thing, I’d love to see it. Drop what you're working on or just say hi! 👇
English
286
9
234
13.1K
Marko Denic
Marko Denic@denicmarko·
Share your websites. Let's get you some traffic!
English
985
12
521
66.9K
OpenAI Developers
OpenAI Developers@OpenAIDevs·
What did you build with Codex this weekend?
English
787
41
1.5K
382.4K
Leonidas Maliokas
Leonidas Maliokas@PlayingInCanvas·
@TTrimoreau Quite nice already! We launched in early access a few days ago, getting nice feedback from first users to tweak and improve responses.
English
1
0
1
16
Thomas Trimoreau
Thomas Trimoreau@TTrimoreau·
Hey founders ! Looking to connect with people building in: 🍽️ SaaS 🚀 Tech 📲 Automation 🧠 AI tools 📱 Product Development 🔥 Web APP Drop what you're working on👇
English
219
3
213
10.1K
Leonidas Maliokas
Leonidas Maliokas@PlayingInCanvas·
@startracker @cursor_ai That’s awesome! The VFX sprite edge case is exactly where most AI pipelines fall apart. Clean outlines on static sprites is solved but the moment you add emission or transparency layers it gets messy fast. Smart to iterate publicly like this.
English
0
0
1
24
Startracker 🔺
Startracker 🔺@startracker·
FORGET MY PREVIOUS POST, LET ME BLOW YOUR MINDS! 🤯NEW METHOD! AI 2D SPRITES ARE SOLVED. PERIOD. Day 50 of building a webGL game engine using @cursor_ai 🔽🔽🔽 I was wrong. The previous system had flaws. It wasn't the best. If you use it on VFX heavy sprites, it would start falling apart - either via grain/artifacts, or displacement. But I just couldn't give up. I knew I needed something more. This was the limit the models could give me. So I consulted science: Zheng et al., "Bilateral Reference for High-Resolution Dichotomous Image Segmentation" (CAAI AIR 2024, arXiv:2401.03407) - BiRefNet If any of the brilliant minds who wrote this paper read this post, I'm extremely thankful for your research. It made me solve a really big problem with 2D sprites, and I'm extremely grateful! Thank you! Please reach out if you see this! Now, how does this solution work: 1⃣ Generate your Kling animation (still king for anime 2D style). 2⃣ Run BiRefNet (HR-matting variant rocks) → get solid character alpha. 3⃣ Compute simple brightness/luminance alpha (luma → alpha curve, easy in any tool). 4⃣ Final alpha = max(BiRefNet_alpha, brightness_alpha) — that's it. No fancy weights needed. 5⃣ Feed to your engine / Comfy / whatever. Dynamic lights now play nice with zero artifacts. Mind you, this solution requires an nVidia GPU to run local inference. Alternatively, you can get it done on Colab likely with the free tier! You can try CPU, but no guarantees. Try a lighter model like BiRefNet_lite-2K. Demo is purposely in 30 fps even though I wouldn't run an anime 2D game above 12 fps - for both style and performance. Just wanted to show you the absolute results. Please bookmark this! ☑️ If you love 2D and sprite work, this is truly the best way, the best method I could find. Use it, steal it. Enjoy it! Repost if it saves your workflows too! I think I need a break... almost 40 hours straight solving this. Next are dynamic shadows, and I'm not looking forward to that...
Startracker 🔺@startracker

I MADE THE BEST 2D SPRITE AI PIPELINE EVER! After testing so much, doing tons of math, trying various different methods I finally got truly the cleanest sprite result I could ask for! You should bookmark this post! ✅ I think this is the happiest 'aha' moment I've had since starting this journey. Day 48 of making a custom webGL game engine using @cursor_ai 🔽🔽🔽 I've been trying to solve sprites since I started this project. I came close a couple of times but it was always something - either dynamic lights wouldn't work, or the genAI results would make them grainy, or I would have to have incorrect alpha etc. After so much struggling, wanting to give up, thinking it's impossible - it was finally done! Perfect matte interpolation of black & white backgrounds resulting in a clean outline of the sprite, half transparent effects keeping their full quality. But this was not enough for me. I wanted more. I wanted those dynamic lights for the most badass anime effects that I'll be creating for the next many weeks! And somehow, I managed to come up with the perfect balance that is nice to the eye with almost no visible imperfections or artifacts when using any kind of dynamic lights. See for yourself! 🔽🔽🔽 How does this magic happen? 1⃣ First, the animation is created using @Kling_ai. I found it the best to keep the quality anime 2D style I wanted, but I guess others may work as well. 2⃣ Then, the frames are carefully extracted at lossless quality and processed via automation through Nano Banana pass to create an opposite background (white->black or black->white). 3⃣ Once we have a proper spritesheet, I then used MiDaS to compute the depth maps, and then algorithmically create PBR maps for lighting. The remaining depth maps can also be used for various effects, although haven't explored it much yet. 4⃣ Finally, all elements are cut into single frames and overlapped with their respective normal maps. If done right, they're pretty much ready for runtime. I like my heroes to be 512 to truly stand out like fighting game characters, but all of this works with far smaller or bigger sprites. Mind you, it's important to note that Nano Banana has a max output of 4k. Therefore you don't want to make your atlases larger than 4k - which is still quite a lot since it allows you 8x8 512 frames. 💡💡💡 I believe the output quality is beyond anything currently available, and I'll be looking into packaging the whole thing into a web app so people can use it. If you find this useful, please repost it! I really wanted to share this method to the world. Thank you for reading! Look forward to day 49 update!

English
48
56
906
67.5K