Dado

176 posts

Dado

Dado

@Dadojvk

Katılım Nisan 2026
77 Takip Edilen4 Takipçiler
Dado retweetledi
Ethan Brooks
Ethan Brooks@alt_w_v_g·
My wife mentioned a nice private school over dinner this week She said the campus was beautiful I asked what's the tuition She said we should look at it as an investment in him not a cost I made a note She said don't make a note I said I always make notes She said this isn't a deal I said everything is a deal She closed her eyes She said we'd discuss it Saturday I agreed Saturday 7:02am She came downstairs in her Saturday robe Coffee in hand I had my cargo shorts on The dining room had been cleared The projector was on The analyst was at the head of the table Quarter zip on, three iced coffees, a legal pad, and two laptops He had been there since 6:44am I texted him at 11:14pm Friday The text said dining room 6:45am bring the model He sent a thumbs up My wife stopped in the doorway She said what is this I said you said you wanted to discuss it She said this is not a discussion I did not respond She sat down anyway The analyst stood He said good morning ma'am She did not respond He sat back down A printed deck in front of each seat A fourth copy in case Slide 1 Tuition Schedule $38,500 per year Thirteen years $500,500 nominal Before escalators The school has raised tuition 4.2% per year for a decade With escalators $648,000 My wife said okay I said I'm not done Slide 2 Opportunity Cost Even before escalators $38,500 invested annually 10% nominal return S&P long-run average since 1928 By his eighteenth birthday $944,000 My wife said we can afford it I said I know that's not the slide Slide 3 Terminal Value at Age 65 $83 million She was quiet The analyst slid the sensitivity tables across the table 8% return $31 million 10% return $83 million 12% return $222 million She did not look She said this isn't about money I said it's always about money She said no it isn't I said then what is it about She did not answer She said you can't put a dollar value on his teachers his classmates his environment I said I can the analyst already did slide 6 He flipped to slide 6 She did not look She said the school is the best in the city I said best is a feeling She said it produces the best students I said the students were already the best before they got there She said our son deserves it I said our son deserves $83 million My son walked in He is five Dinosaur pajamas He looked at the projector He looked at the open deck on the table He looked at slide 3 He said are we modeling pre-tax or after-tax The analyst opened a new tab My wife looked at the ceiling He said what's the discount rate The analyst set down his pen She closed her eyes He said is this the same return assumption from the 529 conversation The analyst stopped typing He looked at me I did not say anything She stood up Sat back down He said dad can I help I said yes He pulled up a chair The analyst handed him a printout He started reading My wife watched him read She watched him for a long time She said his name He looked up She said do you like school He said the work is too easy and the kids don't ask questions She did not respond She looked at the ceiling She walked out of the room The analyst started packing up He said should I follow up Monday sir I said no follow up needed He'll be fine Sent from my iPhone
Ethan Brooks tweet media
English
415
591
7.8K
1.4M
Dado retweetledi
Gary Simon
Gary Simon@designcoursecom·
What's strange to me is that there's a bunch of really sick visual experiments being achieved with @threejs /tsl, but very few actual games. This is one of the best ones I've seen so far.. Give me more examples!
English
34
19
471
37K
Dado
Dado@Dadojvk·
The correct way to think about skills is as “loadouts” in a video game. You select a group of skills, rules, etc. that you need to have a certain experience with the code or system. You share those loadouts so others have a consistent experience.
Mark Kretschmann@mark_k

I'm really not a fan of Skills in agentic AI systems. They add unnecessary complexity and open up a whole new set of problems, especially once Skills can be downloaded and suddenly need versioning, trust, compatibility, and package management. I understand why they are useful right now. But the more general these AI systems become, the less they should need this extra layer.

English
0
0
0
4
Louis Lsvr
Louis Lsvr@LouisLsvr·
how many of these bench tests are paid for? Composer 2.5 is not a frontier model except if you have a stake in Cursor or if you have a price bias.
BridgeMind@bridgemindai

New CursorBench results just dropped. Two big takeaways. Composer 2.5 is way better than most people think. 63.2% score at $0.55 per task. Nearly matching Opus 4.7 Max and GPT 5.5 Extra High at 20x less cost. This is insane value. Gemini 3.5 Flash is #10 at 49.8%. Below GPT 5.5 Low. Below Opus 4.7 Low. Google's newest model can't even beat budget tier competition. Composer 2.5 is the sleeper. Gemini 3.5 Flash is the disappointment.

English
53
1
62
33.8K
Dado
Dado@Dadojvk·
@ericzakariasson @LouisLsvr IMO it's rude how there is no opt-out from the composer-2.5 fast version. I tried to reverse engineer the agent cli binary because it literally can't use composer 2.5 non-fast, and the IDE doesn't support non-fast subagents. 6x forced higher cost!
English
2
0
4
747
eric zakariasson
eric zakariasson@ericzakariasson·
@LouisLsvr if you’ve tried it and disliked it, curious to hear how we can improve!
English
11
0
89
6.9K
Spenser Dickerson
Spenser Dickerson@SpenserFX·
Synthetic splat training from a single image using the new Pixal3D + Trellis 2 backbone.. 9.4m polygons wrapped up into a 9mb splat asset.. over 200 image to splat assets made over the weekend, now just training a few data sets to see how they look
English
3
3
49
3.2K
Will Eastcott
Will Eastcott@willeastcott·
splat-transform is a free and open source library and CLI tool for processing 3D Gaussian splats. It can create lightweight, accurate, voxel-based collision at scale. No human intervention required. This gym scene's voxels are perfectly generated - even large fully transparent windows are correctly filled. The voxel data file is 118KB. Start building 3D Gaussian splat apps today with @playcanvas and splat-transform. 🧑‍💻
English
9
43
365
18.9K
Dado retweetledi
John Loeber 🎢
John Loeber 🎢@johnloeber·
I agree that the bottom half of earners should pay zero federal income tax. My reason for it is different: it's about clarifying who pays. Right now you have tens of millions of people paying painful taxes, and they're under the impression that their taxes make a difference. They assume that the government budget is funded by taxpayers exactly like them, they've been told that the rich aren't paying their fair share, and so forth. The reality is different: the income taxes paid by these people are negligible (~1.6% of total federal tax revenue). It doesn't really matter. But it has an enormous political impact: they believe that by paying these dollars, they are core contributors, and the outrage press has them believe they're getting short-changed for their contributions. The reality is the opposite, they are net beneficiaries by a long shot. As usual, there is a huge difference between "almost zero" and "zero" -- taking their contributions down to zero would make it abundantly clear that they are net beneficiaries, pure recipients, not payers. The value that this provides in terms of restoring some sanity to political discourse will probably outweigh the equivalent loss of tax revenue.
English
68
124
1.9K
162.1K
David Virant
David Virant@DVirilis·
@Youssofal_ Oh neat! How did you set this up? I had some trouble routing it from Ollama, but didn't really continue because Hermes ended up working so well
English
1
0
0
181
Youssof Altoukhi
Youssof Altoukhi@Youssofal_·
Managed to get QWEN 3.6 27B running in Cursor with localhost (no Ngrok) at 120 - 140 TPS on 2x 3090s.
English
36
9
307
20.4K
Dado
Dado@Dadojvk·
@koguGameDev Pixal3D is amazing and I've been very pleased with the results, though manual re-alignment to the grid is required still, unfortunately, for most assets.
English
0
0
2
955
kogu
kogu@koguGameDev·
なんと、ローカルで動かせる最新の3D生成モデル「Pixal3D」がライセンスをMITに変更、素晴らしい! 元は商用を禁じた研究用ライセンスだったため、かなり抑えたテストしかしてませんでした。モデルもコードもMITとなったからには、ローカルでの主力としてもっと活用していきます。 コードとモデルはこちら。 github.com/TencentARC/Pix… huggingface.co/TencentARC/Pix… Pixal3Dは近年の3D生成が、画像からの生成時に「より正しい形状」に寄せることで、元の画像から乖離した結果となる点を改善目指すもの。 現在はMSのTRELLIS.2ベースにしたものが公開されていて、これが今回商用にも制限のないMITライセンスになりました。素晴らしい。
Wang Zhao@WangZhao_0849

‼️UPDATE: Pixal3D is now under the MIT License. We hope this makes Pixal3D easier to use, build upon, and adopt for broader research and applications. Thanks again for your support, and feel free to let us know your feedback!

日本語
2
253
1.5K
194.4K
kogu
kogu@koguGameDev·
3D生成のRodin( @DeemosTech )Gen-2.5でテストした1000万ポリゴン出力。画像1枚からメッシュのみ。
日本語
6
24
256
14.5K
Dado
Dado@Dadojvk·
@heyvasos Did you try Trellis.2 and Pixal3D? I’ve found Pixal3D blows them all out of the water.
English
0
0
1
32
Vas Feofanov
Vas Feofanov@heyvasos·
Tested 3 AI 3D generators in 2026: Rodin AI wins - only one whose output ships to Three.js without ~2 hrs of cleanup. Meshy AI: faster iteration, missed polygons. Tripo AI: really weird result. By the way, all of them are good and you need choose a model depending on task. Added videos for comparison.
English
9
16
151
8.3K
Dado
Dado@Dadojvk·
@WangZhao_0849 Pixal3D is amazing and using it a ton already! Is there an automated way to solve the grid alignment problem? My team is having to rotate the assets manually after generation.
English
0
0
2
917
Wang Zhao
Wang Zhao@WangZhao_0849·
‼️UPDATE: Pixal3D is now under the MIT License. We hope this makes Pixal3D easier to use, build upon, and adopt for broader research and applications. Thanks again for your support, and feel free to let us know your feedback!
Wang Zhao@WangZhao_0849

🚀🚀 Introducing Pixal3D (SIGGRAPH’26) — a new pixel-aligned image-to-3D generation paradigm for high-fidelity 3D asset creation. Today’s Image-to-3D has become pretty good at producing plausible 3D assets. But plausibility is not enough. Fidelity is a hidden bottleneck. ❓A generated model may look “about right,” yet still fail to truly align with the input pixels. Can we make 3D generation as faithful as reconstruction, while still allowing it to complete the unseen? Pixal3D is our answer. 💡We believe the core bottleneck behind fidelity is 2D–3D correspondence. Most 3D-native generators synthesize shapes in canonical space and inject image cues through cross-attention, forcing the model to implicitly search for which pixels correspond to which 3D regions. 🍀Pixal3D takes a different route. Instead of generating in canonical space, Pixal3D generates directly in pixel-aligned camera space — what you see is what you get. The generated 3D asset is aligned with the input view from the start. ☕️Meanwhile, Pixal3D introduces back-projection-based image condition scheme - explicitly back-projects multi-scale pixel features into 3D voxels, thus resolving the 2D-3D association problem. The input image is no longer just a prompt - it becomes a geometric anchor. 🚩Pixal3D shows that pixel-aligned 3D generation is not only feasible and scalable, but also significantly improves fidelity, pushing 3D-native generation closer to reconstruction-level faithfulness. It also naturally extends to multi-view and scene-level 3D generation. ✅Faithful to the input view. ✅Generative for the unseen. Closer to reconstruction-level fidelity, with the creativity of 3D generation. Pixal3D also represents an effort towards the unification of 3D generation and reconstruction. 📢Paper, code, and demo are fully released — try it out and let us know your feedback! 🌐Project page: ldyang694.github.io/projects/pixal… 🤗Huggingface Demo: huggingface.co/spaces/Tencent… 💻Code: github.com/TencentARC/Pix… 📄Paper: arxiv.org/abs/2605.10922

English
21
154
1.2K
286.4K
Dado retweetledi
NVIDIA AI
NVIDIA AI@NVIDIAAI·
Most language models only generate one token at a time. We just released Nemotron-Labs-Diffusion, a family of diffusion language models that take a different approach, generating multiple tokens in parallel within a single model. Rather than committing to each token permanently, these models can revise as they go, resulting in faster inference that better utilizes modern GPUs. The full model family ranges from 3B to 14B, including vision-language variants. Available now: nvda.ws/4tEnTxP
GIF
English
42
191
1.2K
89.8K
Dado retweetledi
Google
Google@Google·
We asked our agents to build a working operating system from scratch using @Antigravity 2.0 and Gemini 3.5 Flash. It took: ⏱️ 12 hours 🤖 93 parallel sub-agents 🔄 15k+ model requests 🧠 2.6B tokens processed 💸 Less than $1K in API credits To build a functioning OS from scratch. #GoogleIO
English
299
376
4.4K
689.2K
Dado
Dado@Dadojvk·
@Trinkle23897 @pg_dons Yeah I got 93% on a cloud detection task, have to check how well it generalizes now
English
0
0
0
19
Jiayi Weng
Jiayi Weng@Trinkle23897·
@Dadojvk @pg_dons You cannot explain what a neural net is doing but you can see what a heuristic policy is doing
English
2
0
0
73
Jiayi Weng
Jiayi Weng@Trinkle23897·
Very exciting to see the cool result! Same pattern, different physics: Codex-grown heuristics matching or beating DRL agents in fluid dynamics, while staying readable, maintainable, and transferable. Heuristics were not dead. They were under-maintained.
pg@pg_dons

1/5 TLDR; We used Codex to discover and maintain heuristic learning for hard fluid dynamics control cases. I’ve been applying DRL and GNN to physics since 2019,, and over the past 3 months I’ve been toying with the idea of using agents in our processes. Inspired by the blog post from @Trinkle23897, I decided to use the same strategy and have agents find readable control strategies. This means a lot to our field, where interpretability can be key for industry.

English
3
34
214
33.6K