Marija_ comments on Anthropic says it can read Claude's 'thoughts,' as detailed in new research paper — models observed to have a global workspace, revealing more of what makes LLMs tick

Anthropic says it can read Claude's 'thoughts,' as detailed in new research paper — models observed to have a global workspace, revealing more of what makes LLMs tick (www.tomshardware.com)

submitted 4 months ago by cm0002@lemy.lol to c/Aii@programming.dev

6 comments fedilink hide all child comments

you are viewing a single comment's thread
view the rest of the comments

[–] Marija_@programming.dev 1 point 3 months ago

Understanding model behavior seems more valuable than chasing bigger benchmarks.