tech, startups, internet

Safety built into LLMs creates new risks.

Safety built into LLMs creates new risks. “malware developers added nuclear & biological weapons text to to their spyware. Goal? To trigger LLM safety refusals… so that their spyware wouldn’t be analyzed by an AI security scanner.” ~ learn more

better doing

When safety proves dangerous

Farnam Street discusses risk compensation, like driving faster because we strap on our seat belts. “Understanding how it affects our behavior can help us make the best possible decisions in an uncertain world.” | learn more