VAI

220 posts

VAI banner
VAI

VAI

@levainbey

🎮

Katılım Ağustos 2014
464 Takip Edilen1.8K Takipçiler
VAI retweetledi
-shi.v-
-shi.v-@mickle_shiv·
fuck the supreme court
English
0
1
2
60
VAI
VAI@levainbey·
local identity.md from yesterday (1)
English
0
0
0
42
Cosmo Mídias 🔶
Cosmo Mídias 🔶@CosmoMidias·
A Blur Texture node group using Repeat Zone in #b3d Shader Editor. (Nodes in the comments).
English
4
19
263
13.7K
FR33 🗽
FR33 🗽@Rcr8tor·
God please give me money for Art
English
1
5
21
278
VAI
VAI@levainbey·
Ai needs something to read 🍔
English
0
0
0
37
VAI
VAI@levainbey·
VAI tweet media
ZXX
0
0
1
44
VAI
VAI@levainbey·
VAI tweet media
ZXX
0
0
1
35
VAI
VAI@levainbey·
i've always loved ROM Hacks so I'm making my own.
English
0
0
1
62
VAI
VAI@levainbey·
@threejs you have my vote
English
0
0
1
33
Three.js
Three.js@threejs·
100,000 followers 🤗
English
48
8
408
13.8K
Taelin
Taelin@VictorTaelin·
seriously, working with AI is MISERABLE for one and only one reason: having to re-explain the same thing "oh yeah this new session obviously doesn't know what proper case trees are, so let me explain it for the 5000th time in my life" I'm tired AGENTS.md doesn't solve this because it is impossible to fit the entire domain knowledge without nuking the context - it would be 1m+ tokens worth RAGs don't solve this, the agent won't search unknown unknowns SKILLs don't solve this unless I keep like a collection of 1750 skills with specific cuts of domain knowledge for each possible subset of my domain that I might need in a given chat, but that's a lot of manual work recursive LLMs or whatever don't solve this for the same reason, you can't dump a domain book and expect the AGENT will magically guess that it is supposed to search for a specific bit knowledge. unknown unknowns fine tuning doesn't solve this (OSS models suck and OpenAI / Anthropic gave up on user fine tuning) I honestly think a good product around fine tuning on your domain would be a major hit and an underdog lab should take this opportunity
English
667
180
3.5K
249.4K
Kieran Parker
Kieran Parker@_kprkr·
Can anyone more talented than me help me understand how to create this natural-feeling inky-blotch effect? All my shit comes out feeling not-so-natural. And if you say AI you best come with a prompt.
Kieran Parker tweet mediaKieran Parker tweet media
English
29
9
768
54.4K
Sahaj
Sahaj@iamsahaj_xyz·
Introducing orbserve reconstruct images from physics particles in a beautiful, interactive & customizable simulation
English
11
20
260
15.3K
Google Workspace
Google Workspace@GoogleWorkspace·
Create files straight from your chats with Gemini ✨ Generate PDFs, Microsoft Word and Google Docs, Excel and Google spreadsheets & more — just say what you need and the format. No templates or extra steps needed. Available now to all users on Gemini web and mobile → gemini.google.com
English
39
153
1K
189.4K
Gregory Wieber
Gregory Wieber@dreamwieber·
Alright, Codex with GPT 5.5 is completely cracked. This is nuts 🤯 Basically one-shotted my request to create an app that takes a prompt, creates an equirectangular panorama with GPT image 2 – and then use Apple's ML Sharp to stitch a gaussian splat world together.
English
76
233
4.3K
846.7K
VAI
VAI@levainbey·
@Roblox wtf? cool
English
0
0
0
55
Roblox
Roblox@Roblox·
Procedural Models are here! Create editable 3D models with code or AI in Roblox Studio. Made with attributes that you can shape and refine. What will you create? devforum.roblox.com/t/studio-beta-…
English
201
186
2.3K
525.9K
VAI
VAI@levainbey·
@googlegemma i see OpenCode mentioned in a Google Gemma tweet > i click the tweet
English
0
0
0
366
Google Gemma
Google Gemma@googlegemma·
Unplugging completely! No WiFi and zero notifications. A great way to get deep focus on a project. Here is a walkthrough showing how to run Gemma 4 (26B A4B) fully offline with LM Studio & OpenCode to parse PDFs, ask questions, and build sites 100% locally.
English
51
337
3.5K
230.6K