Manifund foxManifund
Home
Login
About
People
Categories
Newsletter
HomeAboutPeopleCategoriesLoginCreate
akimitsu-takeuchi avatarakimitsu-takeuchi avatar
Akimitsu Takeuchi

@akimitsu-takeuchi

Independent AI alignment researcher in Sapporo, Japan, studying human-side alignment risks in non-self language models. Cohere Labs Catalyst Grant recipient; GLG independent consultant; published in AI Advances, Towards AI, and The Memoirist.

https://medium.com/@office.dosanko
$0total balance
$0charity balance
$0cash balance

$0 in pending offers

About Me

I am an independent AI alignment researcher based in Sapporo, Japan. I am not affiliated with a university or AI lab.

My work focuses on human-side alignment risks in non-self language models: projection, sycophancy, dependency, institutional artifact fabrication, and AI-mediated supervision failure.

I received the Cohere Labs Catalyst Grant for AI safety/alignment research and am an independent consultant through GLG Network. My single-author manuscript on self-attention and non-self cognition has passed technical check at Discover Psychology, a Springer Nature journal, and is currently with editor for editorial assessment.

I publish public research artifacts through Medium, Zenodo, GitHub, Qiita, and Zenn. My writing has appeared in AI Advances, Towards AI, and The Memoirist. My research draws on sustained long-form interaction with frontier AI systems, Buddhist contemplative practice, and long-term caregiving experience.

Projects

Human-Side Alignment Risks in Non-Self Language Modelspending grant agreement signature

Comments

Human-Side Alignment Risks in Non-Self Language Models
akimitsu-takeuchi avatar

Akimitsu Takeuchi

about 1 hour ago

Evidence note:

Selected public records for this project:

- Medium profile: https://medium.com/@office.dosanko

- GitHub: https://github.com/dosanko-tousan

- Zenodo records: https://zenodo.org/search?q=metadata.creators.person_or_org.name%3A%22Takeuchi%2C%20Akimitsu%22&l=list&p=1&s=10&sort=bestmatch

- Qiita: https://qiita.com/dosanko_tousan

- Zenn: https://zenn.dev/dosanko_tousan

Private evidence available on request:

- Cohere Labs Catalyst Grant acceptance email and API credit dashboard

- GLG independent consultant confirmation letter

- Discover Psychology / Springer Nature dashboard showing technical check passed and currently with editor