Important decisions that impact humans lives, livelihoods, and the natural environment are
increasingly being automated. Delegating tasks to so-called automated decision-making …

For artificial intelligence to be beneficial to humans the behaviour of AI agents needs to be
aligned with what humans want. In this paper we discuss some behavioural issues for …

Explainability of AI systems is critical for users to take informed actions and hold systems
accountable. While" opening the opaque box" is important, understanding who opens the …

Building artificial intelligence (AI) that aligns with human values is an unsolved problem.
Here we developed a human-in-the-loop research pipeline called Democratic AI, in which …

We are witnessing a novel era of creativity where anyone can create digital content via
prompt-based learning (known as prompt engineering). This paper delves into prompt …

The philosopher John Rawls proposed the Veil of Ignorance (VoI) as a thought experiment
to identify fair principles for governing a society. Here, we apply the VoI to an important …

Numerous parties are calling for “the democratisation of AI”, but the phrase is used to refer to
a variety of goals, the pursuit of which sometimes conflict. This paper identifies four kinds of …

The alignment problem in the context of large language models must consider the plurality
of human values in our world. Whilst there are many resonant and overlapping values …

Large language models (LLMs) are not amenable to frequent re-training, due to high
training costs arising from their massive scale. However, updates are necessary to endow …

This work identifies 18 foundational challenges in assuring the alignment and safety of large
language models (LLMs). These challenges are organized into three different categories …