Home        Donate

Nick Kross’s AI Alignment Page

I’m Nicholas Kross, and I do AI alignment research in my spare time.

Profiles: LessWrong, AI Alignment Forum, Effective Altruism Forum, Twitter

Conceptual

• Abstraction is Bigger than Natural Abstraction [30 May 2023]
• My AI Alignment Research Agenda and Threat Model, right now (May 2023) [27 May 2023]

Mathematical

• TBA

Fieldbuilding

• Dreams of “Mathopedia” [1 June 2023]
• Why and When Interpretability Work is Dangerous [27 May 2023, last updated 18 May 2023]
• [SEE EDIT] No, You Need to Write Clearer [29 April 2023, last updated 2 May 2023]
• A Quick List of Some Problems in AI Alignment As A Field [21 June 2022]
• Quick Thoughts on A.I. Governance [22 April 2022]

Other

• Why I’m Not (Yet) A Full-Time Technical Alignment Researcher [24 May 2023]

This organizational setup will likely change in the future, as I gain clarity on different lines of research and how to organize these pages.

This sub-site is hosted inside Thinking Much Better, though not necessarily licensed or authored or owned in precisely the same way. On this sub-site, the below statement overrides Thinking Much Better’s default licensing:

Unless otherwise specified on individual pages, all posts in this sub-website are licensed under a Creative Commons Attribution 4.0 International License.