Sveriges mest populära poddar

Data Skeptic

Debiasing GPT-3 Job Ads

49 min • 10 oktober 2022

We hear about the impeccable achievements of GPT-3 models, but such large generative models come with their bias. On the show today, Conrad Borchers, a Ph.D. student in Human-Computer Interaction, joins us to discuss the bias in GPT-3 for job ads and how such large models can be de-biased. Listen to learn more!

Förekommer på
00:00 -00:00