Ai Alignment And Safety
-
-
What would Hannah Arendt say about AI alignment?
4 min read -
How to use causal influence diagrams to recognize the hidden incentives that shape an AI…
16 min read -
In the previous part of this series, I introduced counterfactuals and showed how to encode…
14 min read -
For a more just world, a collective effort is necessary.
5 min read -
AI Alignment and Safety There is a plethora of content on differential privacy (DP), ranging…
7 min read -
![An agent trained to do a backflip using human feedback and reward modelling. Source: [2]](https://towardsdatascience.com/wp-content/uploads/2021/11/1vvu7QAz-x0zYn9xlBQthuA.gif)
An AI-safety minded perspective on the risks of Reinforcement Learning agents learning their reward functions
15 min read -
AI Alignment and Safety Why aren’t we more worried that no one can explain what…
5 min read -
A guide to the technology, its vulnerabilities and possible mitigations
8 min read -
It is not the technology at fault, but the intention
6 min read