Expanding AI Control from Models to Harnesses — LessWrong

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…

x Expanding AI Control from Models to Harnesses — LessWrong AI "Agent" Scaffolds AI Control AI Frontpage 17 Expanding AI Control from Models to Harnesses by fastfedora 15th Jul 2026 24 min read 0 17 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 same time, Claude Code and Codex have both implemented their own version of both action-based and source co

related reading

• The case for ensuring that powerful AIs are controlled — LessWronglesswrong.com
• Countering misuse of AI: September 2026 / Anthropicanthropic.com
• A basic systems architecture for AI agents that do autonomous research — LessWronglesswrong.com
• Welcome to Learn Harness Engineeringwalkinglabs.github.io
• A Guide to Claude Code 2.0 and getting better at using coding agents – sankalp's blogsankalp.bearblog.dev
• AI Control: Improving Safety Despite Intentional Subversion — LessWronglesswrong.com
• Don’t Outsource Your Thinkingteltam.github.io
• Best practices for Claude Code - Claude Code Docsanthropic.com
• The Case Against AI Control Research — LessWronglesswrong.com
• Harness design for long-running application developmentanthropic.com
• Effective harnesses for long-running agents \ Anthropicanthropic.com
• Vulnerability Research Is Cooked - Quarrelsomesockpuppet.org