menu_open Columnists
We use cookies to provide some features and experiences in QOSHE

More information  .  Close

MIT researchers studied 16 million election-related AI responses. They found chatbots are ‘sensitive to steering,’ raising questions about LLMs’ neutrality

2 0
previous day
The researchers found that, to varying degrees, the models’ responses tended to be swayed by users sharing demographic information.

© Fortune