Tom McGrath
Find the best settings for SAE training we can, then scale across models
Oliver Habryka
Funding for LessWrong.com, the AI Alignment Forum, Lighthaven and other Lightcone Projects
Casey Clifton
Helping charities drive policy change
Dan Hendrycks
Open Paws
Building ethical AI for all sentient beings, fostering safer AI practices for human and non-human animals.
Effective Altruism New Zealand
Presenting an AI safety paper, STARC
Charbel-Raphael Segerie
We are writing an AI safety textbook designed to serve as a comprehensive educational resource for the field.
Thane Ruthenis
Ammon Lam
Kyle Gracey
Improve policy, communications and campaign coordination, and increase trust, among AI ethics & safety organizations, and provide capacity building to new orgs
Louis S. Berman
AI-Risk Education for Politicians
A mana based Poker event for Manifold users
Jeroen Willems
A Happier World explores exciting ideas with the potential to radically improve the world. It discusses the most pressing problems and how we can solve them.
Zian Bonoan
Your contribution makes a difference at EA Philippines!
Glen M. Taggart
By rapid iteration on possible alternative architectures & training techniques
Ambreen Deol
RCT with predominantly Asian Indian population and literature review for understanding mechanisms of IF in relation to T2DM
Emily Kerr-Finell
An effective, replicable, self-sustaining model to sustainable economic success for migrants via microbusiness
Karpov
I plan to investigate what realistic RL training conditions might lead to LLMs developing steganographic capabilities.