Back to All Events

#1 Dr. Dan Hendrycks on the history of CAIS (Center for AI Safety) and the current state of catastrophic AI Risk

About the event

In this very first event of the ALIGN webinar series, we invite Dr. Dan Hendrycks, who is one of the leading figures in promoting both technical research and field-building activities in AI safety. He is the founder and current director of the Center for AI Safety (CAIS).

We will hear from him about the brief history of CAIS, what drew him into this field, the current state of catastrophic AI risk, and finally, his expectations for ALIGN and Japanese stakeholders.

  • Date: Friday, 17 May 2024 10:00 am-10:55 am (JST) = Thursday, 16th 6:00 pm - 6:55 pm (PDT)

  • The talk (including the discussion part) will be recorded and posted on ALIGN’s Youtube Channel.

ALIGN Webinarシリーズの第1回では、Center for AI Safety (CAIS)の創設者であり、AIセーフティの分野の技術的研究や提言活動で世界を先導する一人であるDan Hendrycks(ダン・ヘンドリックス)博士をお招きします。CAISのこれまでの歩み、Hendrycks博士がこの分野で活動するに至った経緯、AIが抱えるリスクの現状についてトークいただきます。

  • 日時:2024年5月17日(金)10:00 am-10:55 am (日本時間)

  • 英語のイベントです(質疑は日本語でも可能)。

  • イベントは議論部分を含めて録画のうえ、ALIGNのYoutubeチャンネルにて公開予定です。

Agenda

  • 10:00-10:05 am announcement from ALIGN

  • 10:05-10:35 pm Dr. Hendrycks on the history of CAIS (Center for AI Safety) and the current state of catastrophic AI Risk 

  • 10:35-10:55 pm Q&A and discussion with participants

Selected papers by Dr. Dan Hendrycks

  • Hendrycks, Dan, Mantas Mazeika and Thomas Woodside. “An Overview of Catastrophic AI Risks.” ArXiv abs/2306.12001 (2023)

  • Hendrycks, D., Burns, C., Kadavath, S., Arora, A., Basart, S., Tang, E., Song, D.X., & Steinhardt, J. (2021). Measuring Mathematical Problem Solving With the MATH Dataset. ArXiv, abs/2103.03874.

  • Hendrycks, Dan, Nicholas Carlini, John Schulman and Jacob Steinhardt. “Unsolved Problems in ML Safety.” ArXiv abs/2109.13916 (2021)

  • Hendrycks, Dan. “Natural Selection Favors AIs over Humans.” ArXiv abs/2303.16200 (2023). featured in TIME

Intended Audience

  • Anyone interested in AI Alignment/AI Safety research (not necessarily currently engaged in it).

  • Our hope is to invite many audience based in Japan and discuss field-building activities in the Japanese context, but nevertheless we welcome access from around the world.

Next
Next
18 May

#2 Tan Zhi Xuan on the pluralism in AI Alignment: philosophy, governance, and research