A global workspace in language models

·LessWrong··

[This is the blog post for our new paper Verbalizable Representations Form a Global Workspace in Language ModelsReaders might also be interested in: the Public commentary, Github and Neuronpedia]As you read this sentence, circuits in your brain are adjusting your posture, controlling your breathing, and transforming lines and curves on the screen into recognizable words. Most of this processing is invisible to you. But some of what takes place in your brain you do have access to—an image that po...

Read full article →

Related Articles

What Emily Bender meant by "stochastic parrots"
digital55 · Hacker News · 4h ago
Nintendo announces new product revisions in Europe with replaceable batteries
akyuu · Hacker News · 6h ago
Road to Elm 1.0
wolfadex · Hacker News · 7h ago
Car touchscreens are cheap, not good
citelao · Hacker News · 3h ago
OpenWrt One – Open Hardware Router
peter_d_sherman · Hacker News · 1h ago