I wonder how well this model can typecheck Ruby code.
Realistically only at static time
There's no code or weights released => no way to reproduce their results.
They may not have linked the source in the paper, but it's not hard to find: https://github.com/Kaiwen-Tang/Sorbet
Haven't checked if there's enough there to build it.
Thank you very much for posting this! The code is indeed there, that's great.
Results get reproduced without code or weights all the time. I note that in this case training data and evaluation benchmarks are public.
The ML community has historically held themselves to a higher standard, IME.
sometimes it seems folks are just making up words.
neuromorphic hardware is just hardware that has biologically inspired designs.
spiking neural networks are artificial neural networks that actually simulate the dynamics of spiking neurons. rather than sums, ramps and squashing, they simulate actual spike trains and the integration of energy that occurs in the dendrites.
neuromorphic hardware can range from specialized asics for doing these simulations efficiently to more experimental hybrid analog-digital systems that use analog elements to do more of the computation.
it's all very cool stuff, but i tend to think of snns as similar to the wings on the avion 3 where simplified unit functions look more like a modern jet wing.
but who knows, maybe the neuromorphic route will open the door to far more efficient computations. personally, i'm very excited about potential wins that could come from novel computational substrates!
And even with a willingness to make up words, it’s STILL hard to name tech projects uniquely: https://github.com/sorbet/sorbet
I’m flashing back to bapi