Storia in 2 fonti

Misbehaving chatbots could be kept in check with personality tests

Artificial intelligence chatbots need to work on their social judgment, recent events suggest. At one end of the spectrum, they're facing lawsuits for recommending dangerous actions. At the other end, the models can be so nice they're considered sycophantic.

Raccontata da

techxplore.com

the-decoder.com

Confronto fonti

2 prospettive sulla stessa storia

AI · summaries

techxplore.comStai leggendo3 mesi fa

Misbehaving chatbots could be kept in check with personality tests

originale

the-decoder.com3 mesi fa

Making AI chatbots helpful weakens their ability to simulate human behavior, large-scale study finds

A large-scale study covering 208,000 participants and 26 million responses shows that the very training that turns language models into helpful chatbots weakens their ability to replicate human behavior. The effect gets…

Leggi questa versione →

Misbehaving chatbots could be kept in check with personality tests

Confronto fonti

Misbehaving chatbots could be kept in check with personality tests

Making AI chatbots helpful weakens their ability to simulate human behavior, large-scale study finds

Timeline cronologica

The race to regulate AI systems has lawyers getting creative

Misbehaving chatbots could be kept in check with personality tests

Making AI chatbots helpful weakens their ability to simulate human behavior, large-scale study finds