A ChatGPT jailbreak vulnerability disclosed Thursday could allow users to exploit “time line confusion” to trick the large language model (LLM) into discussing dangerous topics like malware and weapons.
The vulnerability, dubbed “Time Bandit,” was discovered by AI researcher David Kuszmar, who found that OpenAI’s ChatGPT-4o model had a limited ability to understand what time period it currently existed in.
Therefore, it was possible to use prompts to convince ChatGPT it was talking to someone from the past (ex. the 1700s) while still referencing modern technologies like computer programming and nuclear weapons in its responses, Kuszmar told BleepingComputer.
Safeguards built into models like ChatGPT-4o typically cause the model…
Boutique Travel VC raises investment cap from $1.5M to $10M to lead rounds and support portfolio companies through growth Travel...
Read moreDetails
