The results of the #TesseractHackathon are finally out. Congratulations to the winners, and a huge thanks to all participating teams! 
We’ve seen some amazing contributions pushing the boundaries of differentiable systems that we want to introduce below 
First prize: Multi-Agent Differentiable Predictive Control for Zero-Shot PDE Scalability, by Pietro Zanotta et al.
How can agents in a moving liquid collaborate to shape their environment without communicating with each other? Multi-Agent-DPC answers this question by exploiting a differentiable PDE solver, wrapped as a Tesseract. A brilliant showcase of how differentiable programming at the systems level drives real innovation 
Second prize: DeepSwingr – A Differentiable Framework for Cricket Ball Swing Optimization, by Pavan Govindaraju
An ambitious project implementing end-to-end trajectory optimization that uses no less than four Tesseracts, two of which are higher-order Tesseracts 
We love the engineering + care poured into it, and how it demonstrates that Tesseract scales well to complex cases like this one.
Social media prize for the most viral submission: PruneDeepONet by Tomoki Koike
Competition was tough. There were three particularly strong honorable mentions:
- diffopteract: Differentiable Optimization via JAX <> Julia interoperability with Tesseract by Laurens Lueg
- DiffPIC: Differentiable Particle-in-Cell Optimization with Tesseract by Alejo Ballester et al.
- Backend-Agnostic Inverse 1D Burgers Solver via Tesseract by Julian Chan
Keep an eye out on our socials + the Tesseract Forums for more in-depth showcases of select submissions, and thanks again to all participants 