PhD in EE, former AI researcher, now in strategic planning. I aim to spot and share the changes that advancing technology will bring—before they arrive.
New Google Gemma 4 12B claims near-26B performance - we tested both!
We ran both models locally on one RTX 4090 and gave each the same task: write a self-contained HTML5 canvas animation with real physics in one file without libraries. Three scenes - a Galton board, two blocks colliding off a wall, and a chaotic triple pendulum
Outputs:
Gemma 4 26B-A4B: 15 GB VRAM usage, 6.9k tokens, 138 tok/s
Gemma 4 12B: 9 GB VRAM usage, 8.9k tokens, 80 tok/s
Same Gemma 4 family, but the 26B-A4B won every scene and ran ~1.7x faster - on just 4B active params. The 12B stayed very close though, on almost half the VRAM - which makes it the ideal model for a 16 GB laptop
✨ One of the most memorable experiences from the @SKhynix booth at #COMPUTEX 2026. Visitors transformed selfies into AI-generated portraits inspired by Korean culture.
SK Group Chairman Chey Tae-won joined the experience too. See the atmosphere 👇
#SKhynix#COMPUTEX2026
야간에 시야가 어두운 이유
썬팅 + 국내차(현기차) 밝기 규정 꼼수 콜라보
2018년 이후 국내 규정(약 2,000루멘 이상 전조등은 오토레벨링과 헤드램프 워셔 필요)
→ 현실은 이 규정을 피하기 위해 1,800루멘 정도로 밝기를 낮춤, 수입차는 이규정 적용받지 않아 보통 2,500루멘이상 적용
현기차는 안전보다 옵션질, 안전보다 원가절감이지 🤦♂️🤦♀️
https://t.co/vWIYqkfOPN
Thanks to the organizers for a great event.
I’ll be here in Denver until Thursday night, hit me up on Xchat if you’d like to get in touch.
Many members of the @Tesla_AI team will be available throughout the conference and can be found at the Tesla booth.
.@aelluswamy will discuss our approach to foundation models for robotics at CVPR today
Room 603, 3:30pm local time
Covering architecture, large-scale multimodal training, end-to-end control, safety & deployment
Come swing by booth 255 for live demos after!
젠슨은 최선을 다해 길 잃은 고객사들을 살리고 있다. 과거엔 GPU만 팔았다면 이젠 무료 컨설팅 + 스타터킷을 함께 제공한다.
“그거… 그렇게 하는거 아닌데…?”
다만 엔비디아의 FDE 들의 태도를 보면, 종종 고객사를 무시하는(이해는 간다) 모습을 보인다.
파트너쉽을 하러 온건지 자기 자랑을 하러 온건지 헷갈린달까?
This week at #CVPR2026, NVIDIA Research is presenting three papers across physical ai that offer groundbreaking solutions for training at scale across diverse applications:
→ GraspGen-X: the first foundation model for zero-shot grasping, trained on billions of simulated grasps
→ LCDrive: a model that replaces expensive text-based reasoning with compact latent representations
→ NitroGen: a generalized gameplay AI foundation model that harnesses NVIDIA Isaac GR00T to help train embodied agents
Learn more: https://t.co/H748YkAWS9
Agents need more than a model.
Jensen Huang breaks down the enterprise agent stack: models, orchestration, tools with skills, and a secure runtime to hold it all together.
This is the NVIDIA toolkit for agents: https://t.co/j6KJhOwZ5B
🏆 Cosmos 3 just topped 7 physical AI leaderboards.
NVIDIA Cosmos™ 3, the open omni-model for physical AI, ranks #1 across world generation, robot action policy, and industrial vision understanding.
🌎 World generation: Artificial Analysis, PAI-Bench, Physics-IQ, R-Bench
🤖 Robot policy: RoboLab
👁️ Vision: VANTAGE-Bench, TAR
One model. Every domain of physical AI.
Available now on Hugging Face ▶️ https://t.co/y9iJ4mO6zh