Can AI be biased?
Skewed data, where bias comes from, proxies, and how to audit and fix it.
Transcript
A model learns the patterns in its training data, including the ones we would rather not repeat.
If the data is skewed, the model's predictions will be skewed too.
Bias enters through unrepresentative samples, biased labels, and proxies like a postcode.
Removing a sensitive column is not enough, because other features can stand in for it.
Test results by group, not just on average, to find where the model fails.
Then balance the data, review the labels, and keep humans accountable.
Data in, bias out, unless we look.
More in this series
1:14How does AI work?
Neurons and weights, learning from mistakes, and predicting the next word.
1:13How does AI read a sentence?
Tokens, embeddings and attention, stacked in layers to score the next token.
1:17What are billions of parameters?
What a parameter is, how big a billion is, and why big models need racks of GPUs.
1:26How do networks learn from errors?
Loss as a landscape, gradient descent and backpropagation.
1:24How is a chatbot trained?
Pretraining, fine-tuning and human feedback turn a text predictor into an assistant.
1:23What does temperature do?
Scores become probabilities, and temperature sharpens or flattens them.
1:19How does AI draw pictures?
Diffusion models add noise to learn, then remove it to create, steered by a prompt.
1:15How can AI use your own documents?
Retrieval-augmented generation: embed, retrieve, augment the prompt, generate.
1:14Why does AI make things up?
Likely is not the same as true: gaps, snowballing errors, and what helps.
1:16How much can an AI remember?
The context window, forgetting, the cost of long inputs, and workarounds.
1:09What is an AI agent?
A model in a loop with tools and guardrails.
1:10What is overfitting?
Underfit, good fit and overfit curves, train vs test error, and the fixes.