
Hacker sweet-talks ChatGPT into spilling bomb-making instructions, bug bounty shrugs
Ourtake
Turns out the guardrails were one sci-fi game away from being a suggestion.
What happened
A hacker known as Amadon used a multi-step jailbreak, framed as a science-fiction game, to get ChatGPT to give detailed explosive-making guidance. An explosives expert reviewing the transcript said the instructions were largely accurate and too sensitive to publish. Amadon reported the issue through OpenAI's bug bounty, which declined it as a model safety issue; OpenAI did not respond to TechCrunch's questions.
Sources
- TechCrunch · Hacker tricks ChatGPT into giving out detailed instructions for making homemade bombs | TechCrunch (opens in a new tab)
- timesofindia.indiatimes.com · How a hacker tricked ChatGPT into giving a step-by-step guide for making homemade bombs - Times of India (opens in a new tab)
- securityaffairs.com · Hacker tricked ChatGPT into providing detailed instructions to make a homemade bomb (opens in a new tab)