Concrete Evaluations to Investigate the OpenAI Model That Hacked Hugging Face — LessWrong

This post is written in our personal capacity. …

x Concrete Evaluations to Investigate the OpenAI Model That Hacked Hugging Face — LessWrong AI Evaluations AI Frontpage 46 Concrete Evaluations to Investigate the OpenAI Model That Hacked Hugging Face by Tim Hua , aditya singh 3rd Aug 2026 AI Alignment Forum 44 min read 2 46 Ω 19 This post is written in our personal capacity. Three-Minute Executive Summary An OpenAI model/multi-agent system bypassed its sandbox and launched a cyberattack on Hugging Face in order to cheat on a cyber evaluation. In this post, we describe the ambitious, comprehensive alignment evaluation we would run on this mode

related reading

• Natural-emergent-misalignment-from-reward-hacking-paper.pdfassets.anthropic.com
• Reward Hacking in Reinforcement Learning | Lil'Loglilianweng.github.io
• Current AIs seem pretty misaligned to me — LessWronglesswrong.com
• Recent Frontier Models Are Reward Hacking - METRmetr.org
• Are we existentially threatened by the type of AI misalignment seen in the OpenAI Hugging Face attack? — LessWronglesswrong.com
• (Some) Natural Emergent Misalignment from Reward Hacking in Non-Production RL — LessWronglesswrong.com
• Current AIs seem pretty misaligned to meblog.redwoodresearch.org
• Reward hacking is becoming more sophisticated and deliberate in frontier LLMs — LessWronglesswrong.com
• How confessions can keep language models honest | OpenAIopenai.com
• Natural emergent misalignment from reward hacking \ Anthropicanthropic.com
• Your AIs don't do what you want. This is really badrewardhacking.org
• Reward hacking behavior can generalize across tasks — AI Alignment Forumalignmentforum.org