The AI Safety Paradox: When 'Safe' AI Makes Systems More Dangerous
AI safety is becoming an established field and science. Yet by focusing only on the safety of individual models, AI labs may actually be making the conditions in which they’re deployed less safe.
Runtime AI, and the Subtleties of Language
Interacting with AI is not a passive experience. It's an ongoing dialogue where our words hold significant sway over the future of the conversation. What does AI literacy mean today? It means paying attention to how our use of language shapes the behavior of AI.