As part of @PrimeIntellect's RL residency program, I've been exploring how to do multi-agent RL using their current stack (from verifiers + prime-rl to lab experiments with hosted training /evals) and thinking about how it could be extended to support these abstractions natively. I've summarized my findings the blogpost below and I'll leave a few comments here, too...
me acuerdo de una vez que el @jeroaranda le preguntó al mero Nocedal si había pensado en usar lentes y óptica para optimización numérica..
bien iluminado mi viejo 🤠
Using light as a neural network, as this viral video depicts, is actually closer than you think. In 5-10yrs, we could have matrix multiplications in constant time O(1) with 95% less energy. This is the next era of Moore's Law.
Let's talk about Silicon Photonics...
1/9
Out today in @RSocPublishing! We show that butterflies and moths accumulate so much static electricity that pollen is attracted onto them across air gaps, meaning they don't even need to make contact with the flower to pollinate it! 🦋🌻 https://t.co/UayKqSCOAc 🧵👇