Why Large Language Models Hallucinate
IBM Technology. Martin Keen sorts hallucinations into four named buckets — sentence contradictions, prompt contradictions, factual errors, nonsense — and walks through each on a lightboard. After the article gives you the why, this video gives you a vocabulary for spotting the type of mistake in the wild so you can decide how much to trust a given answer.
What you should get from this
Martin Keen sorts hallucinations into four named buckets — sentence contradictions, prompt contradictions, factual errors, nonsense — and walks through each on a lightboard.
Watch next
Continue through the same learning path with the next curated companion videos.
42 minutesPrompt Engineering Tutorial – Master ChatGPT and LLM Responses
A longer, more patient course that earns its length.
Watch next
11 minutes4 ChatGPT Hacks that Cut My Workload in Half
Use AI to draft email faster, then pressure-test tone and clarity from the recipient's point of view.
Watch next
90 minutesThe Ultimate Guide to Writing with AI
Use AI as a critical editor for structure, argument and revision without outsourcing your own voice.
Watch nextRelated videos
Take it further
Hand-picked external courses that go deeper on this topic.
Coursera · DeepLearning.AIGenerative AI for Everyone
Real time inside an LLM, learning to prompt deliberately and recognise where generative AI is genuinely useful versus where it's a trap. Calm, no-hype teaching — the perfect bridge from "I've tried ChatGPT once" to "I use it every day with confidence."
Coursera · DeepLearning.AI + AWSGenerative AI with Large Language Models
When practitioners ask "what should I take if I'm serious about building with LLMs?", this is the answer. Mathematically honest without being a research paper; AWS-flavoured deployment chapters stay useful even if you'll never touch SageMaker.
Anthropic AcademyMCP: Build Rich-Context AI Apps with Anthropic
MCP is the protocol that's quietly replacing one-off tool integrations across the AI tooling ecosystem. Learn it from the source. By the end you'll have built and deployed your own MCP server, connected an LLM client to it, and understood why this standard is the closest thing the field has to USB-C.