Pinned Tweet
Hello World ... Its time for ATOMS
An intelligent machine needs three things: a brain, senses, and hands.
We gave AI a brain. We taught it to see. Now we're giving it hands.
Models can propose a thousand hypotheses, but breakthroughs come from testing them.
Today we're launching @primordiant : general-purpose robot scientists that run experiments at scale.
AI mastered bits. Now it's time for ATOMS.
A little overdue, but last month our team was back in Providence, RI, where we had the pleasure of reuniting with Michael Kosterlitz and Sean Ling!
For those who don't know, Mike won the 2016 Nobel Prize in Physics for his work on topological phase transitions, and he and Sean have been close collaborators for many years.
It's always a pleasure catching up with the people who have shaped our journeys as scientists. We're incredibly grateful for the mentorship, conversations, and many years of physics.
The retirement celebration was fittingly called "Mikefest," and we all delayed our flights to make sure we could attend! Congratulations on your retirement, Mike!
Primordiant retweeted
Both. Teams who don’t want to build out their lab infrastructure can use our lab to run experiments with our robots around the clock, or they can buy robots to do things locally in their facilities
Primordiant retweeted
Fun Fact:
We designed, built our first robot and took it into client's wet lab in less than 3 weeks!
They gave it a skull with goggles for Halloween 😂
An intelligent machine needs three things: a brain, senses, and hands.
We gave AI a brain. We taught it to see. Now we're giving it hands.
Models can propose a thousand hypotheses, but breakthroughs come from testing them.
Today we're launching @primordiant : general-purpose robot scientists that run experiments at scale.
AI mastered bits. Now it's time for ATOMS.
Primordiant retweeted
At @primordiant , we build general-purpose robotic scientists on five premises:
1. Hypotheses are cheap. Verification is expensive. During my PhD, I built AI that proposes thousands of dark matter and dark energy models in hours. Testing them takes decades of experiments. That's a gap of about five orders of magnitude.
2. The Bitter Lesson keeps getting confirmed. General methods that scale beat hand-engineered ones.
3. R&D moves fast. Protocols change daily, and many breakthroughs come from someone rethinking the whole experimental setup.
4. Automation isn't automatic. Getting a lab robot to do one task reliably often takes more engineering time than having a person do it.
5. Science should be democratized. Running experiments shouldn't depend on having a big lab.
The breakthroughs we need, from faster compute and cancer cures to fusion power, room-temperature superconductors and the technology that will take us to other planets, won't be found in simulation or theory alone. The answers are in atoms.
#AI #Robotics #LabAutomation #SelfDrivingLabs #Science #DeepTech #Physics #MaterialsScience #YCombinator #DrugDiscovery
Primordiant retweeted
Science doesn’t advance because of good ideas.
It advances because someone built the experiments, ran them. watched them fail, figured out why, and tried again.
As an experimental physicist, I learned firsthand how my physical interactions with my experimental apparatus lead to a difference in results. The bottleneck in science isn’t a shortage of ideas. It’s the ability to test these ideas in a flexible manner at scale.
Today we’re launching @primordiant.
We’re building general-purpose robotic scientists that can operate real laboratory equipment, run experiments, learn from the results, and do it all again.
Science is experimental. It’s time AI got its hands dirty.
Primordiant retweeted
An intelligent machine needs three things: a brain, senses, and hands.
We gave AI a brain. We taught it to see. Now we're giving it hands.
Models can propose a thousand hypotheses, but breakthroughs come from testing them.
Today we're launching @primordiant : general-purpose robot scientists that run experiments at scale.
AI mastered bits. Now it's time for ATOMS.






