Most AI control research such as LinuxArena and Ctrl-Z only gives the red team basic agents which only have access to tools. Yet in 2026, usage of AI within frontier labs has moved to agent harnesses that have access to skills, memory, subagents, external services, compaction and more. At the...
tl;dr: As recursive self-improvement accelerates, we need a top-level agenda to research how to effectively keep humans in the loop. We need to study how humans can best interpret and guide research performed by autonomous agents when those agents lack taste, tacit knowledge or competence, or may try to reward...
Today we are announcing the release of Refactor Arena: a configurable, extensible control setting for exploring how agents might inject vulnerabilities into software applications while performing complex tasks such as refactoring code. In this post, we provide an overview of the setting and, at the end, the results of some...