Towards Alignment Auditing as a Numbers-Go-Up Science — LessWrong

Thanks to Rowan Wang and Buck Shlegeris for feedback on a draft. …

x Towards Alignment Auditing as a Numbers-Go-Up Science — LessWrong AI Auditing AI Frontpage 2025 Top Fifty: 14 % 128 Towards Alignment Auditing as a Numbers-Go-Up Science by Sam Marks 4th Aug 2025 AI Alignment Forum 8 min read 15 128 Ω 62 Thanks to Rowan Wang and Buck Shlegeris for feedback on a draft. What is the job of an alignment auditing researcher? In this post, I propose the following potential answer: to build tools which increase auditing agent performance , as measured on a suite of standard auditing testbeds. A major challenge in alignment research is that we don’t know what we’re

related reading

• Alignment remains a hard, unsolved problem — LessWronglesswrong.com
• LessWronglesswrong.com
• Building and evaluating alignment auditing agents — AI Alignment Forumalignmentforum.org
• Can we safely automate alignment research? - Joe Carlsmithjoecarlsmith.com
• Why I’m optimistic about our alignment approachaligned.substack.com
• Tips for Empirical Alignment Research — AI Alignment Forumalignmentforum.org
• [2602.22755] AuditBench: Evaluating Alignment Auditing Techniques on Models with Hidden Behaviorsarxiv.org
• Research Areas in Benchmark Design and Evaluation (The Alignment Project by UK AISI) — AI Alignment Forumalignmentforum.org
• Auditing language models for hidden objectives — LessWronglesswrong.com
• AGI Ruin: A List of Lethalities — LessWronglesswrong.com
• Building and evaluating alignment auditing agentsalignment.anthropic.com
• Automated Alignment is Harder Than You Think — LessWronglesswrong.com