AI - AI Dynamics

Thanks for your thoughts! I'd also be curious how it extends to embodied AI agents rather than text-based. There are quite a few of us in the human-robot interaction and virtual agent field working on empathy. It would be great to chat and understand more!

→ View original post on X — @petitegeek

22 July 2023

Graph Transformers: Advancing Neural Network Architecture

By

@ceobillionaire

–

22 July 2023 4h07

Attending to Graph Transformers Müller et al.: https://
arxiv.org/abs/2302.04181 #Artificialintelligence #DeepLearning #MachineLearning

→ View original post on X — @ceobillionaire

22 July 2023

Training and Validation Loss Discrepancy in Single Epoch LLMs

By

@esyudkowsky

–

22 July 2023 4h05

If it's just one epoch, why would you expect an important difference between training loss and validation loss? (Unless there's some implicit practice I haven't heard of for LLMs, to use a validation set that isn't just a random holdout from training.)

→ View original post on X — @esyudkowsky

22 July 2023

Perplexity Labs Launches 70B LLaMa Chat Model for Developers

By

@aravsrinivas

–

22 July 2023 4h03

And the 70b LLaMa chat drop on Perplexity Labs! Eg: Implement barebones linear regression in numpy, on https://t.co/vXgu0FfyZ1! Have fun! The latency will improve a lot in the coming days! https://t.co/vymP0z7dxs pic.twitter.com/FugxbQVUY8
— Aravind Srinivas (@AravSrinivas) 22 juillet 2023

And the 70b LLaMa chat drop on Perplexity Labs! Eg: Implement barebones linear regression in numpy, on http://
labs.pplx.ai! Have fun! The latency will improve a lot in the coming days!

→ View original post on X — @aravsrinivas

22 July 2023