liondw
Designer interested in AI safety communication. Working on the Signal-Alignment project to create educational resources for the AI alignment community.
Sydney
Pinned Repositories
Signal-Alignment
An initiative to create concise and widely shareable educational resources, infographics, and animated explainers on the latest contributions to the community AI alignment effort. Boosting the signal and moving the community towards finding and building solutions.
HeuristicImperatives
Reduce suffering, increase prosperity, increase understanding. A proposed framework to address the Control Problem.
RLHI
Reinforcement Learning with Heuristic Imperatives - Finetuning LLMs for Post-Conventional Moral Intuition
HeuristicImperatives
Reduce suffering, increase prosperity, increase understanding. A proposed framework to address the Control Problem.
RLHI
Reinforcement Learning with Heuristic Imperatives - Finetuning LLMs for Post-Conventional Moral Intuition
liondw's Repositories
liondw/Signal-Alignment
An initiative to create concise and widely shareable educational resources, infographics, and animated explainers on the latest contributions to the community AI alignment effort. Boosting the signal and moving the community towards finding and building solutions.
liondw/RLHI
Reinforcement Learning with Heuristic Imperatives - Finetuning LLMs for Post-Conventional Moral Intuition
liondw/HeuristicImperatives
Reduce suffering, increase prosperity, increase understanding. A proposed framework to address the Control Problem.