Alerts
Events
DCR
Explore Cyware Products
Alerts
Events
DCR
Go to listing page
Twitter pranksters derail GPT-3 bot with newly discovered “prompt injection” hack
Threat Intel & Info Sharing
September 17, 2022
ARS Technica
A few Twitter users discovered how to hijack an automated tweet bot, dedicated to remote jobs, running on the GPT-3 language model by OpenAI, using a newly discovered technique called a "prompt injection attack."
Read More
Twitter
Prompt Injection Attack
GPT-3 Bot
Twitter Bot
Hard-coded instructions
Publisher
Previous
CISA orders agencies to patch vulnerability used in Stu ...
Malware and Vulnerabilities
Next
LastPass says hackers had internal access for four days
Incident Response, Learnings
/https://cyware-ent.s3.amazonaws.com/image_bank/1a87_shutterstock_1209143419.jpg)
/https://cyware-ent.s3.amazonaws.com/image_bank/4312_shutterstock_1167591091.jpg)
