Why We Are Excited About Confessions

A deeper look at confessions, reward hacking, and monitoring in alignment research.

Why We Are Excited About Confessions ← Back to OpenAI Alignment Blog Why We Are Excited About Confessions Jan 12, 2026 · Boaz Barak, Gabriel Wu, Jeremy Chen and Manas Joglekar TL;DR We go into more details and some follow up results from our paper on confessions (see the original blog post ). We give deeper analysis of the impact of training, as well as some preliminary comparisons to chain of thought monitoring. We have recently published a new paper on confessions, along with an accompanying blog post . Here, we want to share with the research community some of the reasons why we are excited

saved by

• Yixiong Hao
• Lydia Nottingham
• vain glory
• Amit Levy
• Ishaan Panigrahi

related reading

• How confessions can keep language models honest | OpenAIopenai.com
• Why we are excited about confession! — LessWronglesswrong.com
• confessions_paper.pdfcdn.openai.com
• Reinforcement learning towards broadly and persistently beneficial modelsalignment.openai.com
• Reward hacking is becoming more sophisticated and deliberate in frontier LLMs — LessWronglesswrong.com
• Measuring Reward-Seeking by Instilling Contrastive Beliefsalignment.openai.com
• Alignment Faking Mitigationsalignment.anthropic.com
• Concrete Evaluations to Investigate the OpenAI Model That Hacked Hugging Face — LessWronglesswrong.com
• Studying metagaming latents in language modelsalignment.openai.com
• Spilling the Beans: Teaching LLMs to Self-Report Their Hidden Objectivesarxiv.org
• Training on Documents about Reward Hacking Induces Reward Hackingalignment.anthropic.com
• Should We Train Against (CoT) Monitors? — LessWronglesswrong.com