HOW TO TEACH AI RIGHT FROM WRONG

If we want to get good responses from AI, we may need to see what it does when we ask it to be evil

- MICHAEL WOOLDRIDGE

Today’s AI tools are strange beasts.

On the one hand, they have truly remarkable capabilities. You can ask Large Language Models (LLMs) like ChatGPT or Google’s Gemini about quantum mechanics or the collapse of the Roman Empire and they’ll respond fluently and confidently.

But LLMs can also seem wilfully stupid. For one thing, they get a lot wrong. Ask for a list of key references on quantum mechanics and it’s quite possible that some of the references they produce will be entirely fictitious – ‘hallucinations’ invented by the AI.

Hallucinations are the most prominent of problems with current AI models, but they're not the only one. Just as concerning is that LLMs can easily be steered – deliberately or by accident – into generating wildly inappropriate responses. One notorious incident proved deeply embarrassing for Microsoft, when in 2016 its AI chatbot ‘Tay’ had to be taken offline within 24 hours after being coaxed into producing racist, sexist and antisemitic tweets.

TOO EAGER TO BE HELPFUL

Tay was much simpler than current AI models, but the problem remains – with the right sort of prompt, it’s possible to get an offensive, or even potentially harmful, response from an AI.

The problem comes about firstly because these AIs are designed to be helpful. When you present them with a ‘prompt’, they compute the outcome that seems like the best possible response. For the most part, this is exactly what we want. But the neural networks that underpin LLMs are designed to be helpful in response to