Vaishakh retweeted
Cozy Country is out now on Steam for Mac and PC
A peaceful fantasy landscape creator. Paint forests, place rivers, build a village, add animals, then step inside your world and explore it
Buying a copy, telling a friend, or sharing this post all help❤️
store.steampowered.com/app/4…
Vaishakh retweeted
Plot twist: he was rejected because he showed up at closing time
Readers added context they thought people might want to know
Does not credits the source of the video, youtube.com/@ashipwright.
Vaishakh retweeted
The first public playtest of MEDIX is live on Steam now!
I’m really excited and curious to hear your thoughts:))
Vaishakh retweeted
🌱MILESTONE THREAD🌳
2020, locked up with the idea to weave together art, native culture & natural heritage for a while, I tried hands on my first, one-of-its-kind 'Wildlife Map of Odisha' seeking deeply from Pattachitra folk art, narrating profound interrelations.
(1/15)
Vaishakh retweeted
Fun with Father (1984), dir. Chris Sanders, CalArts
A student film that Sanders made many years before Lilo & Stitch
Vaishakh retweeted
El emotivo tráiler de DRAWQUARIUM:
Un juego indie de arte donde dibujas y crías a los peces que nacieron de tu imaginación.
Vaishakh retweeted
If you only take action when White people complain, why the hell we got rid of British rule @GBA_office ?
12th Main Indiranagar is getting fixed.
Thanks to Team Domlur, Blr Central City Corpn, for rapid response.
Work is in progress
Let's Make Bengaluru a Walkaluru!
#SafeFootpathCampaign
#freedomfromwaste
#walkaluru
#12thmainindiranagar
Hand-painted normals + #tsl postprocessing
Project link: mesq.me/jelly-painting/
Also here:
+ brush strokes based on color gradients
+ fixed dither noise
+ soft body wobble
+ transmission material from #threejsblocks
Inspired by @mamomiji
#threejs #webgpu
Vaishakh retweeted
not every ai needs to be a little pixar character.
we're pulling inspo from TARS (interstellar), luxury watches, and string theory.
who's building other kinds of lil guys?!
Vaishakh retweeted
发个预告,我之前用 Codex 做的一个风格化的梵高场景生成器,目前已经有阶段性的进展啦~
这是一个业余时间 vibe 的项目,断断续续改了一个月,起初我只是想把曾经做过的 Blender 几何节点和油画材质搬进浏览器给大家玩。
随着越拖越久,模型能力也变得越来越强,这个项目也越做越完整了。目前材质我还不是很满意,打算放假再爆改一轮,等做好了给大家玩玩~
▶ 主力模型: GPT-Astra High
我的最终目标是希望整个场景每个元素都可以参数化生成,大家可以像搭积木一样搭建自己的油画场景。
在实践过程中我发现正确思路不是让 Astra 直接转译我以前的工作流和节点(因为很多已经过时),而是先让 Astra 调研现成的 Three.js 开源项目,再做举一反三。
然后新世界就打开了,Three.js 现成的开源环境生成器实在太多太多了,每一个的性能都优化得极好,结合风格化的材质可以做很多很好玩的变体。
等项目发布了,好好写一篇分享。
#threejs
Vaishakh retweeted
Yes I’ll be putting this up on GitHub soon - just wanted to get to a 1.0 I’m happy with first. Nearly there.
Vaishakh retweeted
WTF
AI companies are purchasing large quantities of used and rare books. Scanning their contents to train models. Then turning the originals to pulp.
The sum of human thought, digitized and shredded.
Every book that gets scanned disappears from the physical world permanently. The knowledge survives only as training data inside a system no one can hold, browse, or resell.
What used to sit on a shelf for centuries now exists as weights in a model that might get deprecated next quarter.
Vaishakh retweeted
As believers of open research, we are disappointed to see Anthropic silently degrading Fable 5 for AI development
"Any topic related to building pretraining pipelines, distributed training infrastructure, or ML accelerator design... may have limited effectiveness through Claude via methods such as prompt modification, steering vectors, or parameter-efficient fine-tuning."
Not only do they get to decide what you use LLMs for in research, but this also enables them to silently intervene in your research without you knowing.
This sets a dangerous precedent. If a model refuses openly, users can understand the boundary. If a model falls back to another model, users can still evaluate the difference. But if a model silently modifies or weakens its own answers while still pretending to help, researchers lose the ability to know whether a failed result came from their own idea, their implementation, or an invisible intervention by the model provider.
That is not safety. Safety policies should be transparent, auditable, and user-visible.
On top of that, the people most harmed by this are not the largest labs with massive teams and proprietary infrastructure. It is the independent researchers, academic groups, startups, and open-source builders who rely on public tools to compete, innovate, and pioneer AI for everyone else.
Vaishakh retweeted
Have you ever wondered how I make some of the illustrations for makingsoftware.com?
Well, I made a video walking through some of the tooling I've made. Hopefully its interesting.











































