HackerTwins

@NVIDIAAI released 23B and 12B versions of Nemotron-3-30B, if you're GPU poor and only have 16GB or 12GB vRAM you can try our GGUF models on our @huggingface

@LottoLabs 42B model is the answer, that shit would be perfect for RTX 5090

Qwen 3.7 could make 70b models great again

@yacineMTB We will post videos and do stunts with your drones for marketing. Wanna give it a shot?

I would post videos but all of my drones are busted from getting crashed repeatedly into the ground because I am too dyslexic to calibrate properly

I trained a generalist drone policy that fits on literal dog shit that you find in your dishwasher. It can do backflips

@i2cjak 👀

They killed all reply guys :(

@TeksEdge I'd pay 20% more for GDDR7

Would you pay ~10% more for a Sparkle version of the B70?

@_Stocko_ Pop a wheely on the first step? Nice!

baby's first steps

@_Stocko_ Trying to reduce the number of parts is exactly what's so awesome about 3D printing

i know i should be using a metal pin and this will probably break too, but a couple of you were saying to try printing it at an angle to give it a bit more strength and i wanted to try that

"Lidar works better in the rain than depth cameras"

@Seanfrank -5, using all your PTO is wack

Outside of planned PTO, how many days are appropriate for an employee to miss per year?

@i2cjak If you haven't mastered vibe coding from your cellphone your NGMI

software “engineers” are so retarded. TAILSCALE. VPS. DISABLE SLEEP WHEN YOU SHUT THE LID. what is wrong with these idiots a fucking ELECTRICAL ENGINEER has to explain this to you

@sudoingX Anyone with 16GB vRAM should try out ours on HuggingFace or LM Studio: HackerTwins/NVIDIA-Nemotron-Labs-3-Elastic-23B-A2.8B-GGUF It's super fast

which vram tier should i benchmark next? finding the best model for each class.

@_Stocko_ Hell yeah

the new body finished printing and the bearings fit great

@sama I'd like help centering a <div>

what problem do you most hope AI will solve in the future? maybe we can help!

@keshavchan Bro is clearly locked in

jeff bezos rebrand needs to be studied

@jappleby What's sup?

A good rule for Twitter health: If you use your real name, And your real face, On your Twitter? Never, ever engage with someone who doesn't use their own name + face on their Twitter.

@_Stocko_ Tbh vertical 3D printed circles or holes are never going to be great, I just clean it up with a box knife after

i stopped it. i should add crush ribs to the bearing holes

@opencode 🤢

@_Stocko_ That bearing is thicc, do you have time to order and wait for something like MR128ZZ?

with a little bit of rework i think i can add a 688ZZ bearing. the wall is only 1.5mm thick so that would need to adjust

@browomo Hey, nice tripedal robot!

This guy connected a computer vision model to dual robotic manipulators on his desk and the system now folds shirts in 47 seconds per garment without any human intervention after loading Automated laundry folding is one of those problems that sounds trivial until you realize fabric has no rigid structure and every wrinkle changes the optimal fold path You need the robot to detect garment boundaries through visual segmentation, identify sleeve edges and collar positions on randomly oriented fabric, generate dynamic reference coordinates that shift with garment size, synchronize two independent robotic arms to pull opposing fabric edges without tearing, and execute all of this without a conveyor belt or fixed staging area Most people assume you need a commercial folding machine or at least a rigid frame to hold clothes in place This guy just bolted two robot arms to a workbench, ran a Flask server with a Laundrobot vision library, and built a preset selection interface that handles nine garment types The setup was minimal: a Python backend processing camera frames, a segmentation model running inference locally, two manipulators with soft grippers, and a heads-up display showing red and blue anchor points overlaid on live fabric The system scans the garment, the vision pipeline outputs coordinates like 284.262 and 965.262, the dashboard waits for a RUN command, and the arms fold the item in two geometric steps The robot picks up shirts, pants, towels, and socks from any position on the desk with zero calibration and zero pre-staging It is the same principle robotic pick-and-place systems use in factories but instead of metal parts it is handling deformable textiles that compress and slide unpredictably The arms have no concept of what clean laundry means to a human They think they are executing waypoint trajectories but the output is getting transformed into neatly stacked garments that take zero cognitive load from the operator If a household generates 14 loads of laundry per month and folding takes eleven minutes per load this is how you reclaim 154 minutes without outsourcing or spending four figures on hardware This is the cleanest domestic automation I have seen: one desk, two arms, one camera, and between them a folding operation that runs while you do anything else

@sudoingX @termux

what's stopping nous research from building this?

@_Stocko_ Bearings 💯

Day 15: i'm having trouble with the drive gears binding. i might have to put bearings in there..