# On the "hallucination problem"
I always struggle a bit with I'm asked about the "hallucination problem" in LLMs. Because, in some sense, hallucination is all LLMs do. They are dream machines.
We direct their dreams with prompts. The prompts start the dream, and based on the LLM's hazy recollection of its training documents, most of the time the result goes someplace useful.
It's only when the dreams go into deemed factually incorrect territory that we label it a "hallucination". It looks like a bug, but it's just the LLM doing what it always does.
At the other end of the extreme consider a search engine. It takes the prompt and just returns one of the most similar "training documents" it has in its database, verbatim. You could say that this search engine has a "creativity problem" - it will never respond with something new. An LLM is 100% dreaming and has the hallucination problem. A search engine is 0% dreaming and has the creativity problem.
All that said, I realize that what people *actually* mean is they don't want an LLM Assistant (a product like ChatGPT etc.) to hallucinate. An LLM Assistant is a lot more complex system than just the LLM itself, even if one is at the heart of it. There are many ways to mitigate hallcuinations in these systems - using Retrieval Augmented Generation (RAG) to more strongly anchor the dreams in real data through in-context learning is maybe the most common one. Disagreements between multiple samples, reflection, verification chains. Decoding uncertainty from activations. Tool use. All an active and very interesting areas of research.
TLDR I know I'm being super pedantic but the LLM has no "hallucination problem". Hallucination is not a bug, it is LLM's greatest feature. The LLM Assistant has a hallucination problem, and we should fix it.
</rant> Okay I feel much better now :)
@paulg They're stronger than women, so this would definitely skew the results.
Remember that men also commit 75% of all suicides!
Being a man isn't easy. We have other type of pressures and issues, while being way less likely to seek for professional help.
@bandanjot Have a failed experience of burning $5M and not even launching the product! I'd be keen to share what NOT TO DO.
Today I run a venture studio helping founders finding Product Market Fit, design and launch their ventures. it's somehow "growing"
Love your content by the way 👌
The Brazilian Government has made a tourism ad ahead of the coming election and it’s surprisingly honest and informative! 🇧🇷 #Eleicoes2022
✨ feat guest co-writing & voiceover by Sabrina Fernandes @safbf
@xtinacomputes Your will get a tailored eternal scrolling on social media, search results etc.. that will make you a zumbi, being manipulated without your knowledge as they know you better than yourself!!