✳flâneur — a map of the web's best reading

AI safety technical research - Career review

80000hours.org · 10,058 words · saved by 1 readers

Progress in AI — while it could be hugely beneficial — comes with significant risks. Risks that we’ve argued could be existential. But these risks can be tackled. With further progress in AI safety, we have an opportunity to develop AI for good: systems that are safe, ethical, and beneficial for everyone. This article explains how you can help. Table of Contents In a nutshell: Artificial intelligence will have transformative effects on society over the coming decades, and could bring huge benefits — but we also think there’s a substantial risk. One promising way to reduce the chances of an AI-related catastrophe is to find technical solutions that could allow us to prevent AI systems from carrying out dangerous behaviour. You’ll need a quantitative background and should probably enjoy programming. If you’ve never tried programming, you may be a good fit if you can break problems down into logical parts, generate and test hypotheses, possess a willingness to try out many different solut

On this page: Introduction 1 Why AI safety technical research is high impact 1.1 Want to learn more about risks from AI? Read the problem profile. 2 What does this path involve? 2.1 What does work in the empirical AI safety path involve? 2.2 What does work in the theoretical AI safety path involve? 2.3 Some exciting approaches to AI safety 3 What are the downsides of this career path? 4 How much do AI safety technical researchers earn? 5 Examples of people pursuing this path 6 How to predict your fit in advance 7 How to enter 7.1 Learning the basics 7.2 Should you do a PhD? 7.3 Getting a job i

Explore this link on the map →

saved by

related reading