My latest at Scientific American. A new study shows that large language models make trade-offs to avoid pain, with possible implications for what some refer to as 'AI welfare' in the future.
www.scientificamerican.com/article/coul...
scientificamerican.com
A New Way to Test AI for Sentience: Make It Confront Pain
A new study shows that large language models make trade-offs to avoid pain, with possible implications for future AI welfare