Загрузка видео...

Не удалось загрузить видео

На главную

This is a great time to learn #robotics! Robot AI has advanced to where a novice like myself can build / train this folding robot in my garage. The tech is not perfect, but it is improving *very quickly* (exciting new papers daily), and will likely be ubiquitous within...

45,791 просмотров • 1 год назад •via X (Twitter)

Комментарии: 12

Фото профиля Philip Fung
Philip Fung1 год назад

another good hardware resource is @viktor_vrp

Фото профиля The Rundown AI
The Rundown AI1 год назад

If you're not learning AI in 2025, you're falling behind. Join 1,000,000+ early adopters reading and learn AI in just 5 minutes a day (for free).

Фото профиля Paul Tan
Paul Tan1 год назад

Joint stiction and insufficient or inaccurate sensor resolution is causing your jitters. Otherwise, really awesome!

Фото профиля Ethan_AI Marketer for 𝕏
Ethan_AI Marketer for 𝕏1 год назад

cool tech, but training can be a pain.

Фото профиля Philip Fung
Philip Fung1 год назад

Imo this is the main pain point of this field, how to scalably generate real training data or properly make simulated data

Фото профиля Damian
Damian1 год назад

Cool. Teleop or autonomous?

Фото профиля Philip Fung
Philip Fung1 год назад

autonomous

Фото профиля Conor Mc Gartoll
Conor Mc Gartoll1 год назад

Great work! Awesome demo

Фото профиля Philip Fung
Philip Fung1 год назад

you inspired me to make the arm!

Фото профиля HumanoidRobots.com
HumanoidRobots.com1 год назад

Nicely done!

Фото профиля Brian Lesko
Brian Lesko1 год назад

Cool demo. Looking like you’re using servo motors, which are often a bit jittery. Do you think AI can smooth and speed up those movements in the future? Right now you need expensive motors and controllers to get smooth motion..

Фото профиля Philip Fung
Philip Fung1 год назад

I suspect this can be smoothed deterministically in software but will have to confirm with a test

Похожие видео

Open source software is GREAT. But "open source" AI is NOT like software - it's VERY different. Rob Miles cuts through the bullshit: ROB: Oh, hey, Meta. I heard Llama's weights leaked. That's rough, man. Information security's hard. How you holding up? META: Oh, we're great. Yeah, we're fine. We... actually, that was deliberate. We meant to do that. ROB MILES: Oh, really? META: Yeah... well, the second time anyway. It's called open source. Look it up. ROB MILES: Oh. Well, I love free and open source software, but do those principles really apply to network weights? How does that work? META: Open source is good for users because it lets them read the source code and see what the program is really doing and how it works. ROB MILES: Wait, have you found a way to tell how a model works by looking at its weights? META: No. But, it lets developers all over the world spot bugs in the code and submit patches. ROB: Wait, people are fixing bugs in Llama's weights? META: Well, no. People can fine tune it themselves, though. ROB: ?? Other companies offer fine tuning through APIs. ... So, hang on, if you can't actually read the code and know what it's doing, then network weights are effectively a compiled binary. So, in what sense is this open source? Why not call it like public weights? Why call it open source at all? META: I love open source. ROB: Well, I know a lot of your employees do, but you don't love anything. You're a giant corporation. What's in it for you? META: I love, love open source.

AI Notkilleveryoneism Memes ⏸️

107,362 просмотров • 2 лет назад