Tag
The article discusses the problem of exploding variance in estimating log-sum-exp functions in machine learning and proposes using least-squares regression to mitigate statistical disadvantages.
This article highlights that benchmark scores for Engrava, a memory layer tool, can vary due to reader or judge stage variance even when retrieval results are unchanged, using LongMemEval results to illustrate the issue.
This paper analyzes whether LLM-generated novels exhibit compressed formal variation compared to human-written novels, finding that AI outputs are more uniform in sentence structure, readability, and punctuation despite individual novels resembling human style.
The article discusses the challenges of building AI native service companies, emphasizing that reducing variance in work quality is critical for trust and scale, more so than operating leverage alone.
The author observes that running the same task with Claude Code across different sessions yields varying decision patterns, making it hard to choose outputs that are safe to ship, and highlights the lack of tooling for evaluating agent decision profiles.