Hacker News new | ask | show | jobs
by YeGoblynQueenne 1121 days ago
We already know that humans are sensitive to meaning. That's not a hypothesis that needs testing.
1 comments
TeMPOraL 1121 days ago
This experiment only proves LLMs are sensitive to meaning too. It was also already known.
link
YeGoblynQueenne 1121 days ago
All I can see with any clarity is that LLMs are sensitive to the user's prompt.
link