Back to All Events

#3 Dr. Evan Miyazono on Atlas Computing’s path to general AI with safety guarantees

About the event

In this ALIGN Webinar, we invite Dr. Evan Miyazono, CEO of Atlas Computing. After completing his PhD in Applied Physics at Caltech, Evan led research at Protocol Labs, where he directed various pioneering coordination mechanisms for metascience and public goods funding, such as hypercerts.

In 2023, he co-founded Atlas Computing, a nonprofit developing AI tools with safety guarantees through the use of an architecture based on formal methods. This initiative will play a complementary role in collaboration with the ARIA Safeguarded AI program, a major government-funded project recently launched in the UK, led by Evan's former colleague, davidad. 

In this webinar, we will hear from Evan about Atlas Computing’s approach to reducing AI risk, why they’re starting by building tools for formal verification, and his metascientific view on the direction of the AI safety field.

  • Date: Friday, 24 May 2024 10:00 am-11:00 am (JST) = Thursday, 23th 6:00 pm - 6:55 pm (PDT)

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

2023年に創設された非営利組織Atlas ComputingのCEO、Evan Miyazono博士を招きします。形式検証の手法に基づいた安全保証付きのAIの開発を目指すAtlas Computingを創設した狙いや、そしてMiyazono氏が長年取り組んできたメタサイエンス的視点から見たAI Safety分野の今後の発展の見通しについて伺います。

  • 日時:2024年5月24日(金)10:00 am-11:00 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 Dr. Evan Miyazono on Atlas Computing’s path to general AI with safety guarantees

  • 10:35-11:00 Q&A and discussion with participants

Selected links to know more about by Dr. Evan Miyazono and Atlas Computing

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.

Previous
Previous
18 May

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

Next
Next
14 June

#4 Dr. Ryan Kidd on the State of AI alignment field building: learning from MATS and LISA