News for hackers. Stuff that matters.
Re:A global workspace in language models by tuvix on Monday July 06, 2026 @05:24PM (#48810695)
I always thought that area of research had the coolest name, too: “mechanistic interpretability”
Re:A global workspace in language models by dr_dshiv on Monday July 06, 2026 @05:34PM (#48810800)
“Machine psychology” sticks with me. So Asimov.