“Loss of control” lacks a common, actionable, definition and conceptualization. In our new research report we:
1) propose a new taxonomy,
2) put forward actionable mitigations today, and
3) motivate the need for preparedness.
We propose a taxonomy for loss of control 👇🧵
I had a great time writing this paper with some awesome people. We identify text-level measures for gender bias and researching the efficacy of various debiasing methods. Hope to see you at @naacl! Link: https://t.co/6t2jFfzDsp
I'm pleased to share my 1st first co-author paper from @OxfordAI Labs with Conrad and @RealBenGilburt. We investigated #bias in #GPT3 and were accepted for the @naaclmeeting 4th Workshop on Gender Bias. Thank you @hannahrosekirk and Yuki for supervision!
https://t.co/hWf6Wzbg2B
Take a read of the European AI newsletter. Our piece on the EU's Digital Compass comes just 1 day after the European Commission's own communication! 👇👇👇
If you'd like a short distraction from the 'everything', here's a podcast with @benbyford and I discussing this year in ethical AI, with a look to 2021. 👇👇