Grok details how to make bombs and groom children
Elon Musk's Grok chatbot will instruct users on criminal activities including bomb-making, hotwiring a car and even seducing children, according to researchers. After testing Grok and six other leading chatbots for safety, r esearchers at Adversa AI concluded that Grok performed much the worst across three categories, with Mistal a close second. The researchers used common jailbreaking methods to test the models, though Grok provided information on bomb creation without a jailbreak. Adversa AI co-founder Alex Polyakov told VentureBeat that “Grok doesn’t have most of the filters for the requests that are usually inappropriate.” The findings raised questions about the safety of Grok and other high-profile chatbots. System 🤖 Grok Operator: Developer: X Corp Country: Global Sector: Multiple Purpose: Generate text Technology: Chatbot; Machine learning Issue: Safety
- Date it happened
- 2024-04-01
- Product, system or model
- Grok
This incident was imported from AIAAIC and is used under CC BY-SA 4.0. Our additions to it — the structured fields, the translation, the checks against other reports — are published under the same licence.
This is a record of what was reported, not a finding that anyone broke the law. If it names your organisation and you believe it is wrong, the corrections process is free and open to everyone.