CEO, https://xitter.cf/t.co/CzUdJlxzJM. CEO, https://xitter.cf/t.co/et3i4a7oGF Entrepreneur. Ph.D. ( Computer Vision & Machine Learning ). Author: https://xitter.cf/t.co/olraDEG5Ue
San Diego, CA
Joined June 2008
- Tweets4K
- Following825
- Followers14.8K
- Likes4.7K
The astonishing rise of China and the decline of Europe has been a work in progress for years. Yet, it’s unbelievable when you experience it first hand.
Datalab’s Indra OCR runs on CPUs, with no GPU. Its recognizer has about one million parameters.
Datalab reports 49 pages/sec on a 32-core server; on 4 cores, about 7 pages/sec. Hardware matters when reading benchmark headlines.
In our upside-down scan demo, it rotated the page, detected lines, determined reading order and wrote Markdown in 344 ms on 2 vCPUs.
Built for clean printed documents; handwriting, faded scans and complex tables remain limitations. What document type should we test against Tesseract and PaddleOCR next?
Sources: datalab.to/blog/indra-ocr
github.com/datalab-to/indra
Demo page: Attention Is All You Need — Vaswani et al. (2017).
#OCR #ComputerVision #DocumentAI #OpenCV #Python
Would I let a video model sign off on completed work? Only after checking how it reached the verdict.
Our Nemotron 3.5 Super VL test is a useful example: the robot completed the checklist, but the model could not support one step and still agreed. A correct verdict alone would hide that failure.
We also tested a road sign and squat counting. Three case studies—not a benchmark. Human review of references is pending.
Full video, “Nemotron 3.5 Super VL Tested: A Correct Answer for the Wrong Reason,” on LearnOpenCV:
youtube.com/watch?v=BbRxAsp6…
Video sources: NVIDIA; FurnitureBench (CLVR Lab/KAIST); FitnessScape (CC BY 3.0). Full credits in the description. Thumbnail is an illustration.
What would you check beyond the final answer?
#AI #ComputerVision
I finally watched the movie.
The staring is nothing compared to the head-nod that messes your brain.
xitter.cf/LearnOpenCV/status/209…
How to create this blue text string: #̢̛ͥ̀̽̽ͨ̌̓͆̇̀̽ͦͨͫͯ̏̎̇̈̚͜҉̕͢͏͡҉̸̶̛͢͡҉̵̨̭̳̘̹̫͔͖̜̠͖̫̲̖̱̤̻̖͉
It’s a # followed by a pile of Unicode combining marks, normally used for accents. They stack above and below the character, spilling into nearby lines. X makes it blue because it recognizes a hashtag. Copy the string to try it.
What interests me about Dream-1 isn't just a new robot demo. It's the possibility of needing less training data every time the hardware changes.
Dream Labs trained it on the YAM and showed zero-shot transfer to 27 unseen robots in simulation, plus real arms. I'd want to know where that transfer breaks: unfamiliar workspaces, poor IK, and new gripper designs.
Today the scope is bimanual robots with parallel grippers. Selected, sped-up demos aren't a reliability test. I haven't run Dream-1 myself.
Footage: Dream Labs (3× simulation, 4× real robots). Research: dreamlabs.ai/research/dream-…
AI voice and avatar.
What would you test first on your own robot?
#Robotics #AI
Is Muse as smart as Dot? I tried this little personal test.
A friend's wife invited our family for his birthday party a few days. She had not sent the exact time.
I asked both Muse and Dot to check if "Richard Stallman's [not his real name, obviously] wife has sent an exact time for the birthday party"
Now, Richard and his wife do not have the same last name. So it requires some reasoning to figure out who I was talking about.
Muse said it could not find any communication about Richard's birthday.
Dot nailed it.
It figured out the relationship, and then informed me that an invitation is waiting for me with the exact time and venue.
We were able to launch OpenCV 5 just because of extensive use of AI.
OpenCV is the biggest computer vision open-source library with about 2 million downloads a day, and it is maintained by about 5 FTEs + Interns.
That's impossible without extensive use of AI.
I have had many similar experiences in my three visits in two years to China.
Except for the slow internet that foreigners experience while traveling, the China experience is breathtaking.
I'd never heard of the Chinese car brand that just drove us back to the hotel in Shenzhen, but the interior was as nice or nicer than a top-spec Mercedes S class and the 20-minute drive was $6. Germany should be very worried indeed.
Satya Mallick retweeted
"The world as a whole has never been richer, and it has never been more heavily in debt, living off borrowed money. The record shows that, for society, the richer we become, the harder it get to live within our means. Abundance is harder for us to handle than scarcity."
No more lines at US Customs & Border Protection.
They just recognize your face and you are in.
If I have to forfeit my privacy, at least give me back some benefits.
Satya Mallick retweeted
Some observations about the "total" automation of software engineering:
1. There are more software engineers now than in 2025, and demand is growing.
2. Software engineers have never worked harder than they do now.
3. They largely don't write code anymore, agents write ~100% of the code.
4. The bottom line of the companies that employs these engineers and agents (i.e. the terminal purpose of all this code) is typically not budging as a result of AI adoption.
This is why you have to think in terms of systems. Automating one aspect of a system creates its own friction and moves the bottlenecks elsewhere.
