Your small guide to: AI Safety
Even when given a very simple goal, an AI can act unpredictably. This phenomenon is known as “specification gaming” or “reward hacking”—achieving the goal that was technically specified, but failing to achieve the actual intended goal. It happens frequently, because it is really hard to explain to a computer what you actually intend for it to do.
Why UK farmed animals could be among Brexit’s unexpected winners?
Although a subsection of people has been arguing forcefully for animal welfare for a long time, it has only really been recently that the idea that we should alter our lifestyles, policies, and practices to accommodate the welfare of animals has caught on.
Forecasting: How and why social sciences can attempt to predict the future
Forecasting can be used to produce evidence for or against a theory by asking, for instance, “if a given theory of international relations were true, what would that predict for the Russia-Ukraine conflict?”
Cults and love: The curious backstory of altruism
We are all familiar with the concept of altruism. And yet, when looking up the definition and doing some research around it, I found out that the term “altruism” is actually a contemporary concept of the 19th Century that doesn’t mean exactly what you would think.
Don’t Look Up: How can fiction spread awareness effectively?
The new Netflix addition takes place in modern-day America and is based around the discovery of a comet that is going to hit the earth, destroying humanity in its wake 6 months from now. We embark on the journey of a team of scientists to fight misinformation, political polarisation and prioritisation of corporations over safety.