In recent years, AI alignment has rapidly developed as a research area where efforts are being made to mitigate the potential risks of AI, including safety, governance, interpretability, and development, with the welfare of humanity as a whole in mind.

This area is also important to WBAI, which aims to “create human-like artificial general intelligence by learning from the architecture of the entire brain” and to consider its impact.

With this in mind, Hiroshi Yamakawa (Chairperson), Yutaka Matsuo (Vice Chairperson), and Koichi Takahashi (Vice Chairperson) participated in the “Japan AI Alignment Conference 2023” held on March 11-12, 2023.

On the first day of the conference, Yamakawa and Takahashi spoke at the “Overview of the Direction of AI Safety Research in Japan” session.

• Hiroshi Yamakawa, Whole Brain Architecutre Approace for AGI development
  Around 1:34 in this video
• Koichi Takahashi, The Automation of science/Robotic biology/Scenarios and branch points to futre machie intelligence
  Around 1:42 in this video

On the second day, Yamakawa gave a talk in the “Participant-driven talks, and open discussion” session.

• Hiroshi Yamakawa, Yutaka Matsuo, Life revolution and Digital sapience
  Around 1:02:26in this video
  Mainly talk about “Hiroshi Yamakawa, Yutaka Matsuo,  Life revolution scenario: Cedes hegemony to a digital life form society to make life eternal,  Preprint at https://doi.org/10.51094/jxiv.313 (2023)”

To activate related activities in Japan, we have established the “AI Alignment Japan Slack Workspace,” where people interested in the impact of AI on humanity and its risks can interact.  Click the invitation link below (with an expiration date) to join us.
https://join.slack.com/t/aialignmentjapan/shared_invite/zt-1scwq3511-HkNNuEfszb7drEGwhynAtw

AI Alignment, researchers, engineers, and students from various backgrounds with a broad interest in AI. We may share new ideas and increase opportunities for collaboration.