AI Large Language Models Security
Accidental LLM Backdoor – Prompt Tricks
In this video LiveOverflow explores various prompt tricks to manipulate the AI to respond in ways we want, even when the system instructions want something else. This can help us better understand the limitations of LLMs.Read More
Large Language Models Security
What is Prompt Injection?
This video is from LiveOverflow. How will the easy access to powerful APIs like GPT-4 affect the future of IT security? Keep in mind LLMs are new to this world and things will change fast. But I don’t want to fall behind, so let’s start exploring some thoughts on the security of LLMs.Read More