
Will Tejeda
@thewilltejeda
Followers
126
Following
2K
Media
374
Statuses
4K
f"{bio}"
Orlando, FL
Joined May 2014
There's always been a fight over the true story of America. I believe deeply in the story that says we’re all created equal, and that if we can treat each other with decency and respect, all of us will be better off.
18K
16K
110K
Excited to release new repo: nanochat! (it's among the most unhinged I've written). Unlike my earlier similar repo nanoGPT which only covered pretraining, nanochat is a minimal, from scratch, full-stack training/inference pipeline of a simple ChatGPT clone in a single,
632
3K
23K
From 3d scan to reverse engineering to prototype in the snap of .... an apple pencil. Gauge pod concept for Chevy Express #shapr3d #revopoint3d #nomadsculpt #3dscan
0
0
5
Introducing Tinker: a flexible API for fine-tuning language models. Write training loops in Python on your laptop; we'll run them on distributed GPUs. Private beta starts today. We can't wait to see what researchers and developers build with cutting-edge open models!
222
773
6K
Splats really are incredible
Think meshes are the best for e-commerce? Think again. 3D Gaussian Splats are fast and cheap to generate...and with the new SOG format from @PlayCanvas, this one is only 5.8MB. 🪄 [1 / 2]
10
9
273
“If you’re looking for new ideas, one way to find them is by looking for heresies.” — Paul Graham, Novelty and Heresy
55
238
2K
Goodbye SOGS, hello SOG! 👋 PlayCanvas open sources Spatially Ordered Gaussians - a new super-compressed format for 3D Gaussian Splatting. https://t.co/XPe1aY4fub
8
75
436
So um.... is this AI ??
0
0
0
BREAKING NEWS FOR CREATORS: Content Creators (YouTubers, Streamers, etc.) no longer have to pay Taxes on Tips or Donations from viewers The Treasury Department added Digital Content Creators in the list of jobs that qualify for the new ‘No Tax on Tips’ deduction
157
497
4K
Here's a full and comprehensive guide for Gemini 2.5 Flash Image (Nano Banana). I'll showcase 20 AMAZING creative use cases for you to try. https://t.co/Pr2RAuOee4 The video is jam packed with value! It's also a full and honest guide that also talks about some limitations.
0
7
48
GPT-5 just casually did new mathematics. Sebastien Bubeck gave it an open problem from convex optimization, something humans had only partially solved. GPT-5-Pro sat down, reasoned for 17 minutes, and produced a correct proof improving the known bound from 1/L all the way to
Claim: gpt-5-pro can prove new interesting mathematics. Proof: I took a convex optimization paper with a clean open problem in it and asked gpt-5-pro to work on it. It proved a better bound than what is in the paper, and I checked the proof it's correct. Details below.
970
4K
25K
Google just released LangExtract Python library. It can extract structured data from unstructured docs with precise sources in just a few lines of code. 100% Opensource.
331
641
7K
Someone just asked Pixar cofounder Ed Catmull about AI. His answer (paraphrased): "AI will create lots of good things and lots of bad things... We don't know where it will go. But it's not going away. So artists need to engage with the technology." #siggraph
46
93
748
Excited to try out @OpenAI GPT OSS with @CerebrasSystems via @OpenRouterAI ! Probably via @OpenWebUI for testing. 3k tokens/sec is insane for o3-mini level performance #vibecode #GPTOSS #Entrepreneurship
0
0
0
Today @Shopify is open sourcing the tool we use for optimizing glTF 3D models. 🔧 Tweak compression settings per texture ⚡ See changes immediately 🧰 Mesh compression options 🌐 Hosted online & free 👇 Check the thread for details
45
290
3K
@andrewpprice Sometimes I do too... Then I look at blender's logo in my desktop and think "why you no do that" and understand that the problem is between the screen and the chair
4
8
176
Sometimes I wonder if we're even using the same software
47
2K
32K
Runway References in my opinion is still the best world consistency building AI tool available and once it's paired with Flux Kontext for making small edits + VEO 3 for lip syncing + sound effects (or Elevenlabs + Heygen Avatar IV for a bit more control over dialogue), you can
20
32
353