Tag
This article shares practical, real-world use cases for LLMs in software engineering, including searching through customer conversations via RAG, triaging API failures from logs, and shortening content. It emphasizes efficiency gains and reducing manual sifting.
A developer's RLM agent processes ~80k lines of CloudWatch logs efficiently, inferring service architecture and finding issues, with plans to open-source it soon.
This paper introduces LogMILP, a weakly-supervised framework for log instance anomaly localization that uses prototype-guided structural modeling and counterfactual perturbation consistency regularization to improve detection and interpretability with only bag-level labels.
This paper argues that log analysis is essential for credible AI agent evaluation, as outcome-only benchmarks often fail to reveal underlying capabilities, safety risks, or failure modes.