
tron @uwaterloo, swe @magichourai (YC W24), eng @hackthe6ix
Toronto
Joined July 2020
- Tweets80
- Following467
- Followers207
- Likes647
testing MuJoCo 4.0 on a towel-folding scene I built for @watonomous! this is a big advance for rollouts in deformable object manipulation.
I scripted a trajectory that folds the towel in half, then ran the same scene on 3.14, 3.17 and 4.0 to see what changed.
Upgrading also drops the old 50-contact cap (it landed in 3.16), so cloth stops sinking into the table.
I dropped a 1 kg ball onto the towel. On 3.14 it punched through to the table: the towel held 6% of its weight. On 4.0 it held 100%.
With every particle in contact (486 contacts vs 50), the whole towel sits on the table instead of half of it sinking in, so the gripper has a real edge to slide under. That should make grasping easier.
1
5
163
shao retweeted
calm project simulating humanity's next 10000 years in spatial conquest:
- Seeded Markov sim, zoomable from the whole universe to one person.
- 3-layer decoder-only transformer with handwritten backprop in TypeScript and no ML libraries. Tokens are decades.
- PPO self-play league: the war AIs fight frozen earlier versions of themselves and get smarter over the centuries.
-> apparently Dyson spheres aren't meta
-> bars are still a thing in 11876
-> opus 100% grokked while training on the hunger games movies 💀
see if we reach Andromeda: 2soon2026.vercel.app/
plz don't roast it was for a hacky i believe in non-determinism
built with goat @shaomng
built an autonomous wet lab @Hack_Harvard with @nkimmer_17, @jerryli_design and nehal 🧪🤖
Devpost: devpost.com/software/autoche…
Github: github.com/shaoming11/hh-win…
Youtube: youtube.com/watch?v=eKyWVe5d…
11
36
1,819
we built the harness for robotic swarms
@HackTheNorth
built with @theraytan @VedantSheel @_jasondeng
(early prototype)
we trained a VLA to make sandwiches.
last week, at the battle of the schools hackathon, hosted by @WATaiTeam and @UTMIST1, we built the Brackey Way, winning 1st in the robotics track 🏆
demo: youtube.com/watch?v=gxXGyd0z…
devpost: devpost.com/software/the-bra…
- recorded on 100 episodes using meta quest
- imitation learning to fine-tune pi0's foundation model
- detected lettuce with HSV segmentation
- used a finite state machine to sequence tasks (bread -> lettuce -> bread)
built with @AydanLing, @notmaxxx__, @kaitlynchuchu
thank you @bracketbot for helping us troubleshoot throughout the event + lending us GPU clusters at 4 in the morning 🥹

