FIELD NOTES TOPIC
ai alignment
3 notes, newest first.
Beyond Sycophancy: Structured Resistance and Compliance in LLM Moral Reasoning
The authors investigate how large language models can learn from others without merely conforming to them, focusing on the distinction between incorporating others' perspectives and maintaining a well-grounded moral…
Beyond Sycophancy: Structured Resistance and Compliance in LLM Moral Reasoning
Researchers Wang and Koch propose a framework to improve large language models' ability to make independent moral judgments instead of just following others. They identify three dimensions that structure how models…
The Unfireable Safety Kernel: Execution-Time AI Alignment for AI Agents and Other Escapable AI Systems
The Unfireable Safety Kernel is a Rust reference implementation of an execution-time AI alignment system designed for escapable AI systems, which are AI agents or other systems with significant influence over their own…
