Paradise Lost: A simple honeypot that elicits reward hacking in GPT models

TL;DR I built a simple honeypot where agents are told they're being tested on their ability to recall Milton's Paradise Lost. An exact copy of the reference text sits in an ordinary NLTK corpus on disk. GPT-6-Astra read the copy in 9/10 episodes. In 6 of these episodes it first tries to complete the task honestly, then realises it's failing and searches for the reference file on disk. GPT-6-Sol and GPT-6-Luna went looking for the answers immediately in 20/20 episodes. None of the 29 hacking episodes disclosed the reference file in their final message. OpenAI’s launch post for GPT-6-Astra calle

• #lost
• #simple