Showing cs.AIShow all
2 papers · 1 filter
cs.AI2026
Architectural Wisdom: A Framework for Governing Optimization in AI Systems
Edward Y. Chang
Modern AI systems exhibit structural failures that capability scaling alone does not reliably fix: they optimize under-specified objectives with no architectural mechanism to quest…
cs.AI2026
Diagnosing and Mitigating Sycophancy and Skepticism in LLM Causal Judgment
Edward Y. Chang
Large language models increasingly fail in a way that scalar accuracy cannot diagnose: they produce a sound reasoning trace and then abandon it under social pressure or an authorit…