José Neto

Senior 3D Graphics Engineer

[José Neto @sonagodela]

https://t.co/K49t3XyIyS

[Steven Brunton @eigensteve]

Free PDF of my new Optimization book:
https://t.co/2QQMQMJqr2

If you like it, check it out on Amazon or at Cambridge University Press!

Please leave a review and email me with any typos/corrections.

[Tom Looman @t_looman]

Unreal Engine 5.8 performance highlights article is live! Focusing on the most interesting changes affecting performance, profiling, and optimization.

New features for profiling with Unreal Insights, tons of shader permutations improvements, and many useful new CVARs and changes that a buried in the full release notes. Find all highlights below:

https://t.co/kWTFhgLi76

[Nikos Papadopoulos @4rknova]

New post: Voronoi Fragmentation of a Mesh.

A full walkthrough: the math, the geometry, clipping against bisector planes, capping, seeding around an impact, verifying shard volumes, performance, and where the method breaks down. Interactive demo included.

https://t.co/CRt2WS1MbT

[Kimi.ai @Kimi_Moonshot]

Releasing the model weights and technical report of Kimi K3.

Kimi K3 is our most capable model: a 2.8T MoE model with native visual understanding and a 1M-token context window.

New model architecture: 2.5x the intelligence per unit of compute, not just more params.

Alongside Kimi K3, we're opening up more of the stack behind it — high-performance attention kernels, MoE communication library, and infrastructure for running agent environments at scale.

Model weights: https://t.co/7m7eEg6Y0B
Tech report: https://t.co/yeu6cjpMCT
Tech blog: https://t.co/YTfiMSNM1f

[José Neto @sonagodela]

@_FNARDINI O melhor narrador dessa copa!

[José Neto @sonagodela]

@gustavoterini @leandrorandrad Tchau

[Kiaran Ritchie @kiaran_ritchie]

You're all doing IK solvers wrong.

The classic methods break down into 3 categories:

1. Analytic
2. Jacobian
3. Geometric

The method I'm proposing improves all three and it's a dirt simple idea you should be embarrassed for not figuring out on your own 🧵

[José Neto @sonagodela]

@IndieGameJoe Stylish!

[Mike Acton @mike_acton]

Using an LLM to optimize code: I created a reference implementation of @kevintracy48's collision detection in C, then used gpt-5.5 to optimize it and managed a > 100x speedup from that baseline. Cost ~125M tokens
Code and details: https://t.co/kXrwN9CFs6

[José Neto @sonagodela]

@LeandroLua61752 @MinDefBahea A @CazeTVOficial precisa encontrar esse cara

[Vincent Alexander @NonsenseIsland]

RIP Marjane Satrapi, the great cartoonist and film director, best known for PERSEPOLIS. She was only 56. A great talent. She will be missed.

[José Neto @sonagodela]

@REDCanids Difícil

[José Neto @sonagodela]

@golsdobrasil1 Vamo @CazeTVOficial faz a boa

[José Neto @sonagodela]

@REDCanids Desse jeito não chega não final

[Zhiyang (Frank) Dou @frankzydou]

Introducing ✨RigidFormer: Learning Rigid Dynamics with Transformers - our attempt to scale learning-based physical dynamics with Transformers.

RigidFormer learns rigid dynamics with Transformers. It is a mesh-free, object-centric Transformer for multi-object rigid-body contact dynamics from point clouds.

Learning physics with purely neural simulators, without relying on traditional physics engines, is an important and widely studied problem. Prior SOTA methods often use graph neural networks for accuracy and generalization, but still struggle with efficient, high-fidelity simulation at scale.

RigidFormer uses only point inputs, matches or outperforms mesh-based baselines on standard benchmarks, runs much faster, generalizes across point resolutions and datasets, and scales to 200+ objects. We also show a preliminary extension to command-conditioned articulated bodies by treating body parts as interacting object-level components.

RigidFormer is mesh-free: it does not require mesh connectivity, SDFs, or vertex-level message passing, making it well-suited for point-cloud observations and scalable simulation.

This architecture can also be adapted to learn soft-body dynamics by replacing the rigid-body module (differentiable Kabsch alignment).

🎬See our video for more details.

Many thanks to my amazing collaborators: Minghao Guo @GuoMh14, Haixu Wu @Haixu_Wu_1998, Doug Roble, Tuur Stuyck @TuurStuyck, and Wojciech Matusik @wojmatusik.

Project page: https://t.co/6TBaRPVEYo
Paper: https://t.co/3OQUSJSND3

[José Neto @sonagodela]

@SAVE_RAL Maravilhoso

[takahiro harada @haradatakahiro]

"Voxel Deformation-Aware Neural Intersection Function" will be presented at Eurographics 2026 this week. It does a ray query to a deformable geom. Still use voxel grids, but now we do DDA in deformed space, convert hit points to rest space, then run MLP https://t.co/d6UmzOEcNE

[José Neto @sonagodela]

@gustavosacy 😢

[Kostas Anagnostou @KostasAAA]

A walkthrough of a selection of Tomb Raider III’s rendering techniques, good read! https://t.co/gqjEVEHfJv

[Tuki @TukiFromKL]

🚨 do you understand what Karpathy just said..

the guy who co-founded OpenAI.. led AI at Tesla.. one of the best engineers alive..

built an app with AI.. and said the code was the easy part..

the hard part was Stripe.. auth.. DNS.. databases.. deploying it.. connecting 15 different services that all have different dashboards and different docs and different billing pages..

AI can write your entire app in 20 minutes.. but it still can't click "confirm email" on Vercel..

so the thing that's "replacing developers" can't do the thing developers actually spend 80% of their time doing..

vibe coding didn't kill software engineering.. it just proved that coding was never the job.. the job was dealing with the mess around the code.. and that mess is still 100% human.