Saved by Kasper Jordaens
AI is learning how to create itself
In most areas of computing, programmers write code or train an AI model to achieve specific objectives, such as driving a car without crashing or generating humanlike text. Stanley creates systems that instead evolve, seeking novelty for its own sake. These systems sometimes discover stepping stones toward solutions that couldn’t be achieved via a ... See more
Maven Is a New Social Network That Eliminates Followers—and Hopefully Stress
When a generative AI system does something, like summarize a financial document, we have no idea, at a specific or precise level, why it makes the choices it does—why it chooses certain words over others, or why it occasionally makes a mistake despite usually being accurate. As my friend and co-founder Chris Olah is fond of saying, generative AI sy... See more
Dario Amodei • Dario Amodei —The Urgency of Interpretability
Perhaps, rather than painstakingly trying to hand-code the things we care about, we should develop machines that simply observe human behavior and infer our values and desires from that.
Brian Christian • The Alignment Problem
about systems that learn from data without being explicitly programmed, and about how exactly—and what exactly—we are trying to teach them.
Brian Christian • The Alignment Problem
Scientists have responded to this challenge by inventing “reinforcement learning,” whereby we do not provide the system with any detail about what it must do (nobody knows!), but only with a “reward,” an evaluation in the form of a quantitative score.5 Even worse, the machine may receive its score after a delay, long after the decisive actions that
... See more