I think to be good at research in bio and biophotonics and comp bio you need to stop trying to follow instructions on how to be a good researcher you need to start optimizing for being a great THINKER. after that, let yourself guide you to your research. - read a lot but choose wisely what you read. a lot of written research in biology is practically lab protocols. if you’re a computational biologist your job is to know how that work is done and do that work, but it is, above all, to stay slightly above the nuances or you drown in them. be highly selective about the papers you truly let IN; some of them may have nothing to do with your particular field, but rare are the papers that aren’t trying to make data, they’re trying to prove and show FRAMEWORKS. hold on to those and understand how to think better. - study math everyday and make your own models of things. of EVERYTHING. - learn to be a systems thinker. always choose systems 2 thinking. - do not get too caught in the bullshit. “it’s a nature paper so it matters” “it’s a stanford paper so it matters” stop thinking like an aristocrat. think like a scientist. when something makes sense, let it click. do not select by huge names and huge institutions. one of my favorite biology papers was written by a guy who has no biology degree. - go back to the classics. there’s far too much people did back then that no one picked up on. learn the history of science. you’ll realize that a big reason why is because those ideas WERE credible but were made out to be a part of a hype bubble (for instance the cloning hype) and many times the authors themselves didn’t realize the INSANE extent of what they were really putting forth - do things. this goes without saying. stop limited your imagination to the data online. the data I needed, needed an instrument that literally didn’t exist so we made it. why? because math and physics allowed for it. reality is your only actual constraint. opinions on reality are getting in the way of your science.

autonomous robot driving through the field at night. no chemicals. no pesticides. just UV light killing pathogens and pests while everyone sleeps. this is @tricrobotics. this is what chemical-free pest control looks like at scale.

theres no competition. because nobody has seen what we have seen

The showing we got for Isaac 1 yesterday was everything we could've hoped for Roboticists, engineers, designers, students, kids, grandparents all in one place Seeing how home robots will change the way we live for the better

👀

Introducing Kits by Tnkr 📦 The fastest way to clone a robot. For Maintainers: distribute your project, BOM to kit in one click. For Builders: everything you need to build it, in one box. tnkr.ai

Lighting differences can make a huge difference in robotics. Today, I found a quirk in my model exemplifying this. > I collected 10h of training data. > 3h in, I notice that the left arm following the right arm for the final movement could be good for the final insertion subtask. > I change behaviour. > But the first 3h didn't include much nighttime data (=dark room). 🎯Result The same policy reliably exhibits different behaviour on exactly this subtask depending on the lighting. So many microlearnings to be made in robotics.

6 foot tall humanoid fights have begun real steel is here

I wonder what those arms are capable of 🤔 (Realtime and autonomous)

『車輪で速く走り、脚で段差や不整地を越える小型ロボット』 点検・救助・探索の機動力を変える。 youtu.be/RTztxJ2dRNI #wheeled #quadrupedal #robot #RobotDog #PhysicalAI #reinforcementlearning #EmbodiedAI #LynxS10 #DeepRobotics

accelerate

Our mission is to make it easy for anyone to deploy a robot to help them in the real world We wrote an intuitive guide to understanding modern robotics, catered toward an audience that understands technology but not AI robotics We hope that this short blog post embeds in you the core principles that will bring further curiosity.

follow this insane based chud now. He’s built his own fucking ACTUATORS bro

This guy is also building robits. His profile is impressive. Check him out. He should have 3k followers, not 323. Out with the slop, in with this cool robit videos!

No clue how @maciint0sh only has 32 followers. The whole robotics community is sleeping on him. He's built his own actuators, driver, arm and more.

Does your machine even harvest chips off old server boards on a Saturday at 10:30pm PST? tuurny.com