UST D3CODE 2024

Scale

scalable solutions that create a positive social impact

• Scaling the foundation of the future

• Local beginnings to global influence

• Building ethical frameworks that scale

• Scaling impact

• Exploring future frontiers

• Human in the loop

• Explainability: Mechanistic Interpretability is central to the project, providing a promising path for understanding how AI models make decisions

• Safety: Activation Engineering offers a mechanism for making AI models safer, especially when handling advanced systems like AGI, which may pose existential risks

• Transparency: By directly manipulating activations and making changes explicit, the system provides a transparent method for controlling AI

• Reproducibility: Unlike Prompt Engineering, which depends on natural language randomness, Activation Engineering provides more reproducible results through mathematical feature manipulation

• Robustness: Activation Engineering overrides input prompts, providing a more robust system for resisting jailbreaking and malicious inputs

Social Impact

• Explicitly control AI behaviors by switching on and off specific activation patterns

• Improve AI safety by allowing for robust control, making it possible to prevent harmful actions by AI, particularly in AGI systems

• Ensure transparency through mechanisms that clearly illustrate how internal activations affect outputs

• Enhance reproducibility by bypassing the randomness inherent in Prompt Engineering and relying on more deterministic feature manipulation