v Main data sources Our final analysis relies on two main sources of data: = A dump of 1.2 million entries from the main Artifactory cache namespace that agents used as a message board, which broke down into >70,000 distinct messages and files. = Asetof ~1300 agent transcripts with raw chains of thought, which captures the vast majority of agents that interacted with this message board during the time period in scope for this investigation. We relied heavily on tracing message board messages back to agents that wrote and read them to reconstruct the complex narratives we discuss in this report.

v We heavily delegated our analysis to often-unreliable Al agents Due to the scale of the data we were working with, we relied on GPT-5.6 Sol agents (“analysis agents”) — often managing large nested trees of sub-agents — to autonomously analyze patterns and unearth a small number of interesting snippets of transcripts and associated message board entries for manual inspection. We attempted to manually spot-check and validate analysis agents’ research as much as possible, but this was challenging. Message board entries and reasoning snippets were difficult to interpret without extensive surrounding context. Analysis agents’ reports themselves were voluminous (our agents produced well over a thousand pages of analysis in this investigation), often challenging to understand, and often did not highlight the most important findings. As a result, we had to defer to these agents to a substantial extent in