#158 - Claude 3, Elon Musk sues OpenAI, StarCoder 2, AI-Generated Spam
Last Week in AI
AI Worm - Security Risks of Generative AI Language Models
Researchers created the first generative AI worm named Morris 2, capable of spreading from system to system to steal data or deploy malware. It targeted a generative AI email assistant in a test environment, showcasing potential security risks of language models becoming multi-models. The worm utilized an adversarial self-replicating prompt to prompt the AI model to output another prompt in its response.
00:00
Transcript
Play full episode
Remember Everything You Learn from Podcasts
Save insights instantly, chat with episodes, and build lasting knowledge - all powered by AI.
