Google’s new neural-net LLM architecture separates memory components to control exploding costs of capacity and compute
Titans architecture complements attention layers with neural memory modules that select bits of information worth saving in the long term.
MIT Technology Review18h
The Download: what’s next for Neuralink, and Meta’s language translation AI
What’s new: Meta has released a new AI model that can translate speech from 101 different languages. It represents a step ...