Host

Nikhil Mahant, MSCA Postdoctoral Fellow, Uppsala University, Uppsala, Sweden.

Description

The visual and literary arts are rife with narratives of AI systems ‘manipulating’ humans or ‘lying’ to them to further their own aims. Some recent academic studies also seem to indicate that AI systems can induce non-ideal mental states (e.g., false beliefs) in their users in pursuing certain objectives e.g., winning a game (Diplomacy), or performing tasks that are out of their reach (solving a captcha).

This workshop will focus on the topic of deception by artificial systems and address some of the following questions: In what ways can AI systems be deceptive? How bad is it that we have chosen to have AI systems behave in an anthropomorphic manner? Do the capacities which make AI systems useful also make them deceptive? Are there conceptual challenges to deceptive alignment in AI systems? What is the significance of deception by AI systems for our societies? How can we address the challenges posed by AI Deception?

The confirmed speakers at the workshop include:

1. Dimitri Coelho Mollo(Umeå University)
2. Jessica Pepp(Uppsala University)
3. Ondřej Krása (University of Pardubice)
4. Rachel Sterken(University of Hong Kong)

Apart from the invited talks, there will be two lightening talks by Kesavan Thanagopal (University of Notre Dame) and Maria Zanzotto (Università degli Studi di Torino)

A provisional program of the workshop (along with abstracts and suggested readings) is available at this link.

Registration information

The conference registration is now closed. If you wish to just attend the workshop, please email the host: nikhil.mahant@filosofi.uu.se