paint-brush
Hallucinations Are A Feature of AI, Humans Are The Bugby@docligot
New Story

Hallucinations Are A Feature of AI, Humans Are The Bug

by Dominic LigotOctober 1st, 2024
Read on Terminal Reader
Read this story w/o Javascript
tldt arrow

Too Long; Didn't Read

Large language models were never meant to be sources of absolute truth. Yet, we continue to treat them as such, using them like search engines or digital encyclopedias, then express shock and dismay when they fall short of our expectations. The truth is, LLMs are incredibly powerful tools for generating language, contextualizing information, and assisting with creative and analytical tasks. But they are not—or at least, not yet—perfect arbiters of fact
featured image - Hallucinations Are A Feature of AI, Humans Are The Bug
Dominic Ligot HackerNoon profile picture

It’s a cycle we’ve seen play out countless times: someone asks a large language model (LLM) a factual question, receives a confident but incorrect answer, and immediately cries foul. “These AI systems can’t be trusted!” “They’re unreliable!” “Look at how it just made things up!” The internet erupts with critics waving the banner of AI’s imperfections, deriding the technology for being riddled with “hallucinations” and fabricating details with the audacity of an overzealous storyteller.


But here’s the thing: large language models were never meant to be sources of absolute truth. Yet, we continue to treat them as such, using them like search engines or digital encyclopedias, then express shock and dismay when they fall short of our expectations. The truth is, LLMs are incredibly powerful tools for generating language, contextualizing information, and assisting with creative and analytical tasks. But they are not—or at least, not yet—perfect arbiters of fact.


If we want to use AI better, it’s time to stop expecting LLMs to perform roles they were never designed for and start leveraging them for what they’re truly good at: aiding human creativity, providing context, and generating possibilities—not absolute truths. Let’s break down why this misconception persists and how we can realign our expectations to get the most out of these models.

Understanding the Nature of LLMs: Statistical, Not Factual

The root of the issue lies in a misunderstanding of what LLMs actually do. Large language models, like GPT-4, are statistical machines at their core. They don’t “know” facts the way humans do. Instead, they predict the most likely sequence of words based on the patterns in the vast amounts of text they’ve been trained on. When you ask an LLM a question, it doesn’t search a database of verified truths. It generates a response based on its understanding of language patterns, which may or may not align with reality.


This is why LLMs are prone to what’s known as “hallucination”—a term used to describe when the model outputs information that sounds

plausible but is factually incorrect or entirely fabricated. Hallucinations happen because the model’s objective is not to verify facts but to produce fluent, coherent, and contextually appropriate text. The more coherent it sounds, the more likely it is to be seen as “true,” even when it’s not.


Expecting an LLM to consistently generate factually accurate information is like expecting a skilled fiction writer to suddenly become a historian. Just because the prose flows beautifully doesn’t mean the content is accurate. When we treat LLMs as authoritative sources, we’re misusing them—and we set ourselves up for disappointment.

The Problem Isn’t AI Hallucinations—It’s Misaligned Expectations

Critics are quick to pounce on AI hallucinations as proof that LLMs are fundamentally flawed. But this criticism misses the point. The problem isn’t that the models generate incorrect information; it’s that we’re using them in ways that demand factual accuracy. We’re holding AI to a standard it was never designed to meet.


Imagine you have a calculator. You wouldn’t ask it to compose a poem and then get frustrated when it spits out a bunch of numbers. That’s not what it’s for. Similarly, asking an LLM to be a definitive source of truth is a misuse of the tool. It’s designed to help us with language-related tasks, like generating ideas, drafting content, or answering questions in a conversational manner—not to be a substitute for fact-checking.


If you need a reliable source of factual information, that’s what databases, search engines, and encyclopedias are for. LLMs can assist in synthesizing information or providing context, but they should be used with the understanding that their responses might not always be correct. Just as we double-check a human’s work, we should verify the outputs of AI models.

Why Do People Keep Using LLMs This Way?

So, why do people keep using LLMs as if they were digital oracles of truth? Part of the reason is that LLMs sound so convincing. They generate language with a fluency that mimics human expertise, often complete with references, citations, and confident assertions. This creates an illusion of authority, leading users to overestimate the model’s reliability. When an LLM generates an incorrect or fictionalized response, it feels like a betrayal, even though the model is just doing what it was programmed to do—producing language, not truth.


Another reason is convenience. It’s tempting to use LLMs as a one-stop shop for answers. They’re fast, accessible, and capable of covering a wide range of topics. But convenience shouldn’t come at the cost of accuracy. Using LLMs for quick answers without verification is like skimming Wikipedia and assuming every word is 100% accurate without cross-referencing any sources. The burden of truth remains on the user.

Using LLMs More Effectively: Playing to Their Strengths

To use LLMs better, we need to play to their strengths. Here’s how:

  1. Creative and Analytical Assistance: LLMs are excellent at generating ideas, brainstorming, and exploring possibilities. If you’re a writer stuck in a rut, an AI can suggest plot twists, character backstories, or article structures. If you’re an entrepreneur developing a new product, an AI can help you articulate your vision, consider new angles, and refine your messaging.
  2. Contextual Understanding: While LLMs may not be sources of truth, they can help contextualize information. They can explain concepts in simpler terms, summarize complex articles, or engage in hypothetical scenarios to explore potential outcomes. This can be incredibly useful for making sense of overwhelming amounts of information or sparking new ways of thinking.
  3. Drafting and Editing: AI can generate first drafts or assist in editing, helping human creators focus on refining rather than starting from scratch. It can speed up content creation processes by handling mundane drafting tasks, allowing humans to apply their expertise in finalizing and polishing the content.
  4. Language and Communication: LLMs can be invaluable for generating responses, crafting emails, or composing speeches. They can be trained to match specific tones or styles, making them useful tools for content that requires a human touch but doesn’t need to be fact-checked line-by-line.

Integrating AI With Human Oversight

The key to using LLMs effectively is to integrate them into workflows that include human oversight. This means verifying facts, cross-referencing sources, and using the AI’s outputs as starting points rather than final products. It’s about using AI as a collaborator, not a replacement for human judgment.


Imagine LLMs as highly capable assistants. They’re knowledgeable, articulate, and quick, but they still need a manager (you) to provide direction, verify their work, and ensure quality. This kind of relationship leverages the strengths of both humans and machines, producing better results than either could achieve alone.

Building Better AI Literacy

Ultimately, the solution to the LLM-as-source-of-truth problem is better AI literacy. Users need to understand what these models are and what they aren’t. They need to be educated about the limitations of AI and the importance of critical thinking when interacting with machine-generated content.


Organizations developing LLMs also have a role to play. Clearer disclaimers, transparency about the model’s limitations, and even built-in fact-checking mechanisms could help set expectations and guide users toward better practices. The goal should be to foster a realistic understanding of what AI can do and how it should be used—because, when used correctly, LLMs can be incredibly powerful allies in navigating information, creativity, and communication.

Let’s Use AI for What It’s Good At

It’s time to stop treating LLMs as fact machines and start seeing them for what they truly are: advanced tools for generating language, aiding creativity, and providing context. They’re not replacements for human expertise or definitive sources of truth, and they shouldn’t be judged as such.


If we can shift our mindset and use LLMs in ways that align with their design and capabilities, we’ll stop getting frustrated by their hallucinations and start appreciating their real value. Let’s use AI better, not as an oracle, but as a partner—one that helps us create, explore, and communicate more effectively while leaving the job of truth-seeking and validation where it belongs: with us.


About Me: 20+ year veteran combining data, AI, risk management, strategy, and education. Social impact from data advocate. Currently working to jumpstart the AI workforce in the Philippines. Learn more about me here: https://docligot.com