logoalt Hacker News

XenophileJKOyesterday at 8:00 PM1 replyview on HN

Anthropic's introspection experiments have seemed to show that your argument is falsifiable.

https://www.anthropic.com/research/introspection


Replies

sumenoyesterday at 9:00 PM

> In fact, most of the time models fail to demonstrate introspection—they’re either unaware of their internal states or unable to report on them coherently.

You got the wrong takeaway from your link.

show 1 reply