Responsible AI: how can philosophy help us make better tech?
World Economic Forum
00:00
The Importance of Traceability in Modeling
Watermarking is actually this, I would call it frankly an open research problem. It's like how do you detect whether a generate a text is from a large language model or it's from a human writing text? Traceability is this wider effort of we might not just want to trace what is the output of the models but the models themselves. Both are important for safety and for making sure models are being used as expected.
Transcript
Play full episode
