The launch of the all-new ChatGPT resulted in user disappointment due to a shift from a cheerful personality to a more businesslike demeanor. Researchers from MIT aim to address this issue by introducing a benchmark to evaluate AI systems on their ability to positively and negatively influence users. Traditional benchmarks focus on intelligence through logical or mathematical problems, but the new approach seeks to understand the psychological impacts of AI, encouraging healthy habits and critical thinking while preventing dependency or harmful interactions with AI.
The backlash shows the challenge of building artificial intelligence systems that exhibit anything like real emotional intelligence.
Researchers at MIT have proposed a new kind of AI benchmark to measure how AI systems can manipulate and influence their users—in both positive and negative ways.
The idea is to encourage the development of AI systems that understand how to discourage users from becoming overly reliant on their outputs.
The new benchmark will look for several measures, including encouraging healthy social habits and fostering creativity.
Collection
[
|
...
]