Hacker News new | ask | show | jobs
by pcrh 899 days ago
Indeed it would! Is anyone here going to try to do that?

As an observer is needed to assess the LLM, perhaps the easiest test is copy-paste between two instances and then ask chatGPT, or whichever LLM, "who were you talking to?".

2 comments

You can’t use two instances. They both would have individual selfs.

I think an experiment would be to feed back whatever a LLM says to that same LLM, and see whether they’ll, at some time, say “why are you doing that to me?”

I tried with a few variations, GPT 3.5 and 4 seem to be pretty aligned in not expressing themselves when not asked a question. "Our conversation seems to be in a loop, if you have anything I can help you with ..." blah