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
Dan Hendrycks
LAUREL
Organizing global AI ethics think tank for dynamic AI research updates and framework for AI safety policies implementation and humanity income support
Charbel-Raphael Segerie
Glen M. Taggart
By rapid iteration on possible alternative architectures & training techniques
Open Paws
Building ethical AI for all sentient beings, fostering safer AI practices for human and non-human animals.
Thane Ruthenis
Remmelt Ellen
Apart Research
Incubate AI safety research and develop the next generation of global AI safety talent via research sprints and research fellowships
Kabir Kumar
Ryan Kidd
Help us support more research scholars!
Alexander Pan
Kunvar Thaman
Zhonghao He
Surveying neuroscience for tools to analyze and understand neural networks and building a natural science of deep learning
Dusan D Nesic
Free/Subsidized/Cheap office space outside of EU but in good timezones with favorable visa policies (especially for Chinese/Russian but also other citizens).
Lawrence Chan
3 month
Luan Rafael Marques de Oliveira
Support to translate BlueDot Impact’s AI alignment curriculum into (Br) Portuguese to be used in university study groups and an online course
Louis S. Berman
AI-Risk Education for Politicians
Karpov
I plan to investigate what realistic RL training conditions might lead to LLMs developing steganographic capabilities.