Yanda

Real-world RL is still too brittle and data-hungry for long-horizon, contact-rich tasks. We introduce Simulation Distillation (SimDist), which turns large-scale simulated experience into reusable world-model priors for rapid real-world adaptation. By combining online planning with dynamics adaptation, SimDist achieves high success rates on tasks requiring precision, force, and reactivity. Play with our interactive visualization to see for yourself: sim-dist.github.io (1/n)

Punchline: distill world models from simulation to enable fast, stable real-world robot adaptation. Simulation is nearly always wrong. But in Simulation Distillation, we ask a simple question: How do we perform simulation pretraining such that real-world adaptation becomes trivially easy? sim-dist.github.io Let's take a closer look (1/n)

Imagine testing your app like real users actually use it. not one fake user clicking through a script, but many users interacting in a single workflow. One uploads a post. Others like and comment on it. In the same test run. In real browsers. @JoveW, @SamuelJepee and I built @qualtydotco a agentic QA that evolves test cases with your product and finally catch the hardest bugs that only show up when users interact. No brittle scripts. No Maintenance.

@pravsels sounds a bit like pointworld, they predict point deltas

began testing this idea over the weekend. what if a World Model takes in the difference between frames as input as opposed to entire frames ? not quite working yet.. but also output isn't completely nonsensical (I'm counting that as a win)

We’re releasing OmniReset, a framework for training robot policies using large-scale RL and diverse resets for contact-rich, dexterous manipulation. OmniReset pushes the frontier of robustness and dexterity, without any reward engineering or demonstrations. Try the policies yourself in our interactive simulator! weirdlabuw.github.io/omnireset/ (1/N 🧵)

Excited to share the project that has surprised me the most in the last year! Large-scale RL in simulation, no demos and no reward engineering can solve dynamic, dexterous and contact rich tasks. The learned behaviors are reactive, forceful and use the environment for recovery in ways that are extremely challenging to bake in or teleoperate! You can play with the policies yourself to see: weirdlabuw.github.io/omnireset/ And, the learned behavior transfers to real world robots from RGB camera inputs! So what’s the trick - using simulator resets carefully! Let’s unpack (1/10)

Hinton, LeCun, and every other neolab: Gradient descent is fundamentally broken. It needs thousands of examples to learn what humans do in only a few. It’s time to start looking for a radical new learning paradigm to close the gap. In-context learning: Do I mean nothing to you?

My child will not be allowed to use chat gpt. He will be smarter and stronger than the other children and he will kill them easily.

@pjreddie no more wow streams? 🤕

I’m working on a new thing, we’re so back…

@doodlestein @lying2them

I wanted to read Henry Kissinger’s 400 page undergraduate thesis (it has an incredible first page), but really didn’t feel like dealing with a scanned PDF that’s annoying to read on a phone without constantly zooming and panning. So I decided to convert it to a nice markdown format using OCR and LLMs. Then I thought it would be nice to fix the footnotes and get rid of the page breaks and to fix the line breaks and other things like that. I was already working on some other coding projects, so I had the idea of loading up the draft markdown file in Claude Code and having it work on fixing these issues using a swarm of 20 sub-agents, which worked well. Then I thought it would be cool to link to the full sources for all the many references on sites like the Internet Archive or Project Gutenberg, so I had another swarm of sub-agents do a ton of searches to track the links down and insert them into the footnotes and bibliography. Then I figured that I might as well run it through my mind-map generator and summarization code to see what it comes up with, so I tried that. But now I had a few files to present, so needed some kind of index page. So I asked Codex with GPT-5 to whip up a slick looking web page to present the stuff nicely, which it did a yeoman’s job with. Note that I was already working with these tools in a bunch of other sessions on other projects, so my work here was occasionally giving some instructions to the coding agents and letting them crank away. I really didn’t spend much active time on this! Anyway, the net result is clearly the premier way in the world today to consume Henry Kissinger’s undergraduate thesis electronically. I’ll post the link in the next tweet to avoid getting punished by the algorithm. As for the thesis itself, it’s wild how erudite he was as a young man, and also what a great writer he was. And even more impressive considering that English was his second language. The thesis is basically him trying to come to grips with, and to mentally organize in an internally consistent way, a vast swath of Western thought. From what I’ve read so far, I think he did a pretty good job. Incidentally, his thesis is the reason Harvard changes the rules to limit the undergrad honors thesis to a maximum of 35,000 words. Good thing they didn’t apply this silly limit to Henry!

@andersonyclin 😭 bro

@BaoYanda srry that was funnier in my head

i need to get better at suffering fr

@tbpn kaiming he not even in the top 30 😭

Two weeks ago, we launched The Metis List. Since then, we've spoken with many of you and have updated the ranking accordingly. 128 top AI researchers, ranked by their peers.

best bowl of ramen ive ever had, only $25

These guys are goated, go download meteor 👀

@evilbiscotto struggling w the waking up early part 😖😵

The problem with all these agent companies/products is that since you don’t have access to the underlying weights, the bet you’re making is that your scaffolds are better than the labs. This is hard because: 1) The labs can bake the scaffolds into the model (Claude Code) 2)

Anyone knows adam?