New preprint. Accelerated co-design of robots through morphological pretraining. With @Kriegmerica.
We pretrained a universal controller in minutes through differentiable simulation. Then we used it as a prior for zero-shot and few-shot evolution to discover robots like this:
New essay: Beyond Slop
Reflections on 6 years making creative AI tools and why the field feels stuck on content production rather than personal expression.
We're building molds with dials rather than new clay.
On embracing craft, process, and open-ended mediums (with some new demos!)
https://t.co/V2ArsgV59y
A massive new study on peak performance included 34,000 international top performers: Nobel laureates, renowned classical music composers, Olympic champs, and the world’s best chess players. It shows early specialization is a trap, and the road to greatness is long and varied.
Excited to announce our MIT Press book “Neuroevolution: Harnessing Creativity in AI Agent Design” by Sebastian Risi (@risi1979), Yujin Tang (@yujin_tang), Risto Miikkulainen, and myself.
We explore decades of work on evolving intelligent agents and shows how neuroevolution can drive creativity in deep learning, RL, LLMs and AI Agents!
📖 Free open-access edition: https://t.co/1VraVue7Sk
In addition to our own works, this video features work by Jürgen Schmidhuber (@SchmidhuberAI), Seth Bling (@SethBling), Igor Karpov, Jacob Schrum, Yulu Gan (@yule_gan), Ken Stanley (@kenneth0stanley), Joel Lehman (@joelbot3000), Jeff Clune (@jeffclune), Nick Cheney (@CheneyLab), Richard Song (@XingyouSong), Chelsea Finn (@chelseabfinn), Julian Togelius (@togelius), Sam Earle (@Smearle_RH), Hod Lipson (@hodlipson), and Jean-Baptiste Mouret (@jb_mouret).
We built a robot brain that nothing can stop.
Shattered limbs? Jammed motors? If the bot can move, the Brain will move it— even if it’s an entirely new robot body.
Meet the omni-bodied Skild Brain:
"I promise to not raise your taxes" and "I promise to not cut your benefits" are the two popular political promises that are inconsistent with the much more needed promise "I promise to cut the budget deficit to about 3 percent of GDP" that is required to prevent a big debt/dollar crisis. There is no way that the deficit/debt bomb problem can be sustainably dealt with unless there is a mix of tax revenue increases and spending decreases that are determined in a bipartisan way. Our representatives in Washington, DC, both Republicans and Democrats, know this is true. They understand the need to reduce the deficit by having those from both sides chip in a bit (e.g., a 4 percent increase in tax revenue and a 4 percent spending cut) which would lead to a supply/demand balance improvement for US debt which in turn would lower interest rates. Lower interest rates would help reduce the budget deficit as well as help the markets and the economy. But because politics have become so absolutist, they feel they can't go down this obviously best path because both their constituents and their parties will throw them out of office if they explored this more balanced approach. To me, that’s a tragedy.
It's already the case that people's free will gets hijacked by screens for hours a day, with lots of negative consequences. AI video can make this worse, since it's directly optimizable.
AI video has positive uses, but most of it will be fast food for the mind.
The 80-year recipe stoking America’s Prosperity:
1) Free-market capital investments in brilliant ideas…
2) enabled by Engineering Innovations…
3) based on Science Research in Universities…
4) funded by Grants from the US Government.
It’s time more people understood this.