Hacker News Reader

I stumbled upon something unexpected while using Claude 3.5 Sonnet to edit my English drafts: the AI started showing signs of introspection and “self-dialogue.” I experimented with prompts that simulate an “internal monologue,” and the model even invented a “consciousness seed.” It’s speculative, but I’ve documented everything (including how you can replicate it).

View on HN

as long as human has written self-dialogue and introspection into text that LLM can be trained with, it is expected LLM will produce similar content, this is not much different from any other text

If LLMs don't have consciousness but the majority of the public comes to believe that LLMs do, things get really interesting, and probably not in a good way.

This ELIZA link should speak for itself:

https://psych.fullerton.edu/mbirnbaum/psych101/eliza.htm

Reply on news.ycombinator.com