Cybersecurity experts are warning about a new type of AI attack
The threat in question is called a "prompt injection" attack, and it involves the large language models that power chatbots.
Stay updated with breaking news from Simon Willison. Get real-time updates on events, politics, business, and more. Visit us for reliable news and exclusive interviews.
The threat in question is called a "prompt injection" attack, and it involves the large language models that power chatbots.
Here's what to know about these type of attacks, which involve the large language models that power AI systems like chatbots.
GenAI is a small piece of the artificial intelligence pie, not the whole pie itself. Keep paying attention to deep learning and machine learning.
IBM Automation’s Jerry Cuomo explained why he and IBM feel that ChatGPT presents myriad risks for enterprises.
Official: "It is simply not feasible to read every book" for depictions of sex.