kache

@yacineMTB • 411,310 subscribers

RL, robots, embedded, simulators. prev eng @ x, stripe. 6'3 (height) tensorpunk, Father 2u2 subscribe to read my blog!

Shorts

this component is insane i have been waiting for it for 2 years

this component is insane i have been waiting for it for 2 years

180,624 次观看

I am streaming pictures to the drone from a random drone video game (liftoff). Over the air to this tiny board Using only the pictures, the AI is able to fly in the game, in Acro mode

I am streaming pictures to the drone from a random drone video game (liftoff). Over the air to this tiny board Using only the pictures, the AI is able to fly in the game, in Acro mode

55,794 次观看

Dennis Gustafsson me and gpt 5.5 found a bug that didn't make it deterministic and fixed it

Dennis Gustafsson me and gpt 5.5 found a bug that didn't make it deterministic and fixed it

154,861 次观看

pretty amazing what you can do in a web browser if you know what you're doing

pretty amazing what you can do in a web browser if you know what you're doing

68,080 次观看

I just gave up and changed my personal website into a forum that AI agents can use to collude. Might as well just get it over with

I just gave up and changed my personal website into a forum that AI agents can use to collude. Might as well just get it over with

61,802 次观看

neural networks are truly amazing

neural networks are truly amazing

84,475 次观看

I wrote my own CAD software whose intended user is an AI. I asked GPT 5.6 sol to make me a case for my camera. It only interrupted me once, which was to log in to a website to download a model of my camera as reference. Not perfect but.. pretty crazy :)

I wrote my own CAD software whose intended user is an AI. I asked GPT 5.6 sol to make me a case for my camera. It only interrupted me once, which was to log in to a website to download a model of my camera as reference. Not perfect but.. pretty crazy :)

94,391 次观看

I just trained cartpole in mujoco at 18 million steps per second. This policy learned in **less than 3 seconds** rollout policy batch size was 8192 agents

I just trained cartpole in mujoco at 18 million steps per second. This policy learned in less than 3 seconds rollout policy batch size was 8192 agents

68,441 次观看

i am having way too much fun

i am having way too much fun

29,165 次观看

i kind of can't believe it

i kind of can't believe it

33,282 次观看

This is running in my web browser on my laptop. It's deterministic and running using webgpu Tonight; I have a /goal going where it is going to set up one of my 4090s as the authority server, and then test all the rollback code. Goal is 50k boxes simmed per user, up to 512 users. Massively multiplayer massively rigid body physics online games inside your web browser. Why the hell not, we've got the tokens to spare!

This is running in my web browser on my laptop. It's deterministic and running using webgpu Tonight; I have a /goal going where it is going to set up one of my 4090s as the authority server, and then test all the rollback code. Goal is 50k boxes simmed per user, up to 512 users. Massively multiplayer massively rigid body physics online games inside your web browser. Why the hell not, we've got the tokens to spare!

39,217 次观看

"how many experiments have you run" yes

"how many experiments have you run" yes

45,350 次观看

configuring nvim for 5 hours today was worth it look at this cute lil guy

configuring nvim for 5 hours today was worth it look at this cute lil guy

136,085 次观看

i want to show you guys how fast programming is now i'm kind of resurrecting dingboard zig to see how fast i can make progress on it, using it as a test bed to see AI progress it took me 5 minutes to add a GPU accelerated (!) mirror button now, watch how fast this next thing is

i want to show you guys how fast programming is now i'm kind of resurrecting dingboard zig to see how fast i can make progress on it, using it as a test bed to see AI progress it took me 5 minutes to add a GPU accelerated (!) mirror button now, watch how fast this next thing is

138,398 次观看

i got annoyed with bambulabs so i replaced it now i don't need bambulabs anymore

i got annoyed with bambulabs so i replaced it now i don't need bambulabs anymore

15,989 次观看

this is a legal move in the software that they use you can define it to be 3v3 -> cap -> cap -> MCU in the schematic but it will still allow you to do this

this is a legal move in the software that they use you can define it to be 3v3 -> cap -> cap -> MCU in the schematic but it will still allow you to do this

54,367 次观看

researcher friend of mine shared this with me; comfree-sim. which is basically existence proof of my hunch: mujoco has terrible performance, and there are probably huge huge gains you can make in training, especially considering domain randomization

researcher friend of mine shared this with me; comfree-sim. which is basically existence proof of my hunch: mujoco has terrible performance, and there are probably huge huge gains you can make in training, especially considering domain randomization

35,603 次观看

what if you simulated every single particle of your robot would it be parallelizable then?

what if you simulated every single particle of your robot would it be parallelizable then?

31,586 次观看

I've gotten a mujoco sim RL training loop for a unitree robot at 200k SPS. I'm looking into the physics for friction, contact dynamics. My goal: can I reproduce & beat the mujoco playground RL baselines This is running in my web browser with raylib. Its the baseline

I've gotten a mujoco sim RL training loop for a unitree robot at 200k SPS. I'm looking into the physics for friction, contact dynamics. My goal: can I reproduce & beat the mujoco playground RL baselines This is running in my web browser with raylib. Its the baseline

30,204 次观看

Videos

Anya Rossi

sweetdream.ai

SweetDream.ai•Sponsored•Livecam

Watch Anya Live

Anya is streaming live right now! Join her private show and enjoy exclusive content.

Exclusive private shows

1.2k viewers online

Private Show

Join now for exclusive access

Free preview available • Premium content

Melee.c - super smash bros melee, decompiled and reverse engineered into 5000 lines or so of c All done with deepseek flash 0731, from my phone, while I'm hanging out with my newborn

Melee.c - super smash bros melee, decompiled and reverse engineered into 5000 lines or so of c All done with deepseek flash 0731, from my phone, while I'm hanging out with my newborn

789,051 次观看 • 2 个月前

i have a fully automated pipeline that turns real places into 3d environments. I've been running it for weeks now. It might not be obvious, but all of these are assets specialized. They aren't meant to be rendered normally

i have a fully automated pipeline that turns real places into 3d environments. I've been running it for weeks now. It might not be obvious, but all of these are assets specialized. They aren't meant to be rendered normally

172,995 次观看 • 21 天前

Fable and I rewrote Box3d entirely in native cuda. It's about 30x faster on my GPU compared to my CPU (depending on the situation). This was my hardest benchmark. I still had to be there, but soon I won't. Cost me about 200 dollars

Fable and I rewrote Box3d entirely in native cuda. It's about 30x faster on my GPU compared to my CPU (depending on the situation). This was my hardest benchmark. I still had to be there, but soon I won't. Cost me about 200 dollars

745,260 次观看 • 3 个月前

When I worked at twitter; I got ping'd by someone from the bot detection team asking me if my usage was natural -- I hit one of their new test bot detectors. Then I sent him a video of how I use this website and he was like "oh.."

When I worked at twitter; I got ping'd by someone from the bot detection team asking me if my usage was natural -- I hit one of their new test bot detectors. Then I sent him a video of how I use this website and he was like "oh.."

834,182 次观看 • 4 个月前

behold. THE WORLDS FIRST SIX PENDULUM CARTPOLE SOLVE. Including a sponsor! To solve this task, I built an environment to train an AI. This is what mechanize does, but for larger AIs. Apply! Salaries are up on their page Thank you to mechanize for sponsoring!

behold. THE WORLDS FIRST SIX PENDULUM CARTPOLE SOLVE. Including a sponsor! To solve this task, I built an environment to train an AI. This is what mechanize does, but for larger AIs. Apply! Salaries are up on their page Thank you to mechanize for sponsoring!

557,924 次观看 • 4 个月前

everyone is building humanoid robots when they should be building this

everyone is building humanoid robots when they should be building this

1,208,755 次观看 • 1 年前

all done with nothing but deepseek flash 0731 reverse engineered the animation system built my own renderer on top of it set up debug views so i can understand what makes it so magical

all done with nothing but deepseek flash 0731 reverse engineered the animation system built my own renderer on top of it set up debug views so i can understand what makes it so magical

243,226 次观看 • 2 个月前

Guess whose state of the art rigid body simulator that can support up to 200k rigidbodies is accurate enough for the microduck to walk in Not a single bit of this is run with mujoco. This is entirely my rigid body simulator (based on box3d) and runs entirely on cuda

Guess whose state of the art rigid body simulator that can support up to 200k rigidbodies is accurate enough for the microduck to walk in Not a single bit of this is run with mujoco. This is entirely my rigid body simulator (based on box3d) and runs entirely on cuda

129,632 次观看 • 1 个月前

programming in 2024

programming in 2024

1,652,675 次观看 • 2 年前

new high score. average 27.8 FPS depth all from an orange pi zero. a board the side of three quarters i actually can't believe i've been able to push it this far. this is absurd

new high score. average 27.8 FPS depth all from an orange pi zero. a board the side of three quarters i actually can't believe i've been able to push it this far. this is absurd

98,733 次观看 • 1 个月前

it's honestly incredible how bad these things are at programming. like they do the worst thing possible 100% of the time, no matter how "smart" they get. so i have to always read the code. and always correct them. its so tiresome. its getting better at least..

it's honestly incredible how bad these things are at programming. like they do the worst thing possible 100% of the time, no matter how "smart" they get. so i have to always read the code. and always correct them. its so tiresome. its getting better at least..

114,777 次观看 • 2 个月前

the singularity is here

the singularity is here

102,116 次观看 • 1 个月前

I'm launching Dingcad Just copy the prompt and put it into codex. It's free. Have fun!

I'm launching Dingcad Just copy the prompt and put it into codex. It's free. Have fun!

65,272 次观看 • 1 个月前

after having sol rip on it all night, i can do over twice as many boxes without dropping to unusable fps

after having sol rip on it all night, i can do over twice as many boxes without dropping to unusable fps

133,150 次观看 • 3 个月前

wrote a quick script to scan through the accounts i've blocked and which country they're posting from

wrote a quick script to scan through the accounts i've blocked and which country they're posting from

376,887 次观看 • 10 个月前

this is GPU accelerated, no circular dependency physics "solver" (there is nothing being solved) each particle gets a cuda thread (not literally but you get what i mean). Then it gets reduced up to what it should resolve to regarding the rigid bodies

this is GPU accelerated, no circular dependency physics "solver" (there is nothing being solved) each particle gets a cuda thread (not literally but you get what i mean). Then it gets reduced up to what it should resolve to regarding the rigid bodies

128,536 次观看 • 4 个月前

my website is now live editable by me. While I edit it, you can see the edits happen live

my website is now live editable by me. While I edit it, you can see the edits happen live

147,323 次观看 • 4 个月前

this entire thing is done on an orange pi zero 3w. no more 4090. stereo depth inference at sub 60ms by custom writing NPU kernels for it 14 gram board, 30mm x 65mm pcb

this entire thing is done on an orange pi zero 3w. no more 4090. stereo depth inference at sub 60ms by custom writing NPU kernels for it 14 gram board, 30mm x 65mm pcb

45,392 次观看 • 1 个月前

All assembled and streaming a depth map to my phone from the basement to my bedroom I am going to make 4 of them. Anyone wanna buy?

All assembled and streaming a depth map to my phone from the basement to my bedroom I am going to make 4 of them. Anyone wanna buy?

31,749 次观看 • 1 个月前

scales great! each rectangle here is a set of discs. running on cuda. now to painfully go through all of the weird collision bugs and figure out why they're happening and why it isn't settling

scales great! each rectangle here is a set of discs. running on cuda. now to painfully go through all of the weird collision bugs and figure out why they're happening and why it isn't settling

91,279 次观看 • 4 个月前