Humans versus Machines: The Hallucination Edition
So many people are confused about the relation between human cognitive errors and LLM hallucinations that I wrote this short explainer: Humans say things that aren't true for many different reasons • Sometimes they lie • Sometimes they misremember things • Sometimes they fail to think through what they are saying • Sometimes they are on drugs • Sometimes they suffer from mental disorders etc LLMs errors result from 𝙖 𝙙𝙞𝙛𝙛𝙚𝙧𝙚𝙣𝙩 𝙪𝙣𝙙𝙚𝙧𝙡𝙮𝙞𝙣𝙜 𝙥𝙧𝙤𝙘𝙚𝙨𝙨. They don't have (e.g., ) intentions, egos, or financial interests, so they don't lie; they don't take drugs; they don't have emotional states. Instead, LLM "hallucinations" arise, regularly, because (a) they literally don't know the difference between truth and falsehood, (b) they don't have reliably reasoning processes to guarantee that their inferences are correct and (c) they are incapable of fact-checking their own work. Instead, everything that LLMs say -- true or false -- comes from the same process of statisti
So many people are confused about the relation between human cognitive errors and LLM hallucinations that I wrote this short explainer: Humans say things that aren't true for many different reasons • Sometimes they lie • Sometimes they misremember things • Sometimes they fail to think through what they are saying • Sometimes they are on drugs • Sometimes they suffer from mental disorders etc LLMs errors result from 𝙖 𝙙𝙞𝙛𝙛𝙚𝙧𝙚𝙣𝙩 𝙪𝙣𝙙𝙚𝙧𝙡𝙮𝙞𝙣𝙜 𝙥𝙧𝙤𝙘𝙚𝙨𝙨. They don't have (e.g., ) intentions, egos, or financial interests, so they don't lie; they don't take drugs;…
related reading
- The Waluigi Effect (mega-post) — LessWronglesswrong.com
- Why AI’s hallucinations are like the illusions of narcissismpsyche.co
- trees are harlequins, words are harlequins - the voidnostalgebraist.tumblr.com
- Hallucination (artificial intelligence) - Wikipediaen.wikipedia.org
- The Future of Everything is Lies, I Guessaphyr.com
- LLM Daydreaming · Gwern.netgwern.net
- Chain-of-Verification Reduces Hallucination in Large Language Modelsarxiv.org
- Prompt Injection as Role Confusionrole-confusion.github.io
- What are AI hallucinations—and how do you prevent them?zapier.com
- Is AI Reasoning Right for the Wrong Reasons? | Quanta Magazinequantamagazine.org
- Hallucination Mitigation using Agentic AI Natural Language-Based Frameworksarxiv.org
- Modifying LLM Beliefs with Synthetic Document Finetuningalignment.anthropic.com