Sign up to save your podcasts
Or
Share In Defense of Black Box AI
Share to email
Share to Facebook
Share to X
Share to email
Share to Facebook
Share to X
Or
In Defense of Black Box AI
Is it better to have a high performing black box AI or a lower performing explainable AI?
Are the explanations for how AI works actually true or really a distortion of what's going on inside the model?
How should we think about and operationalize the tradeoffs between running explainability algos and the high cost and carbon footprint of running them?
These questions and more with Kristof. A really fascinating discussion that reveals the complexity behind simplistic calls for explainable AI.
Kristof is currently leading Responsible AI at JPMorgan Chase. Previously, he helped build out and subsequently led the Responsible AI effort at PayPal. He held various other quantitative roles at major banks and has a bachelors in mathematics and a masters in applied mathematics from the Budapest University of Technology and Economics.
View all episodes
By Reid Blackman
5
1212 ratings
Is it better to have a high performing black box AI or a lower performing explainable AI?
Are the explanations for how AI works actually true or really a distortion of what's going on inside the model?
How should we think about and operationalize the tradeoffs between running explainability algos and the high cost and carbon footprint of running them?
These questions and more with Kristof. A really fascinating discussion that reveals the complexity behind simplistic calls for explainable AI.
Kristof is currently leading Responsible AI at JPMorgan Chase. Previously, he helped build out and subsequently led the Responsible AI effort at PayPal. He held various other quantitative roles at major banks and has a bachelors in mathematics and a masters in applied mathematics from the Budapest University of Technology and Economics.
More shows like Ethical Machines
View all
This American Life
90,549 Listeners
Double Century with Jarrod Kimber
24 Listeners