---
title: "987 * 897 = ? Ask GPT-4, Claude-2, and Perplexity.ai, they all got wrong and Hallucination!"
url: https://daily.dev/posts/987-897-ask-gpt-4-claude-2-and-perplexity-ai-they-all-got-wrong-and-hallucination--w8d6ow5y6
source_url: https://blog.gopenai.com/987-897-ask-gpt-4-claude-2-and-perplexity-ai-they-all-got-wrong-and-hallucination-00812d0f09d1?source=rss----7adf3c3694ff---4
type: article
source: "GoPenAI"
published: 2023-10-25T12:01:26.671Z
updated: 2023-10-25T12:00:58.911Z
tags: ["ai", "machine-learning", "math", "llm", "gpt"]
reading_time: 1
upvotes: 1
comments: 2
language: en
---

> ## Documentation Index
> Fetch the complete documentation index at: https://daily.dev/llms.txt
> Use this file to discover all available pages before exploring further.

# 987 * 897 = ? Ask GPT-4, Claude-2, and Perplexity.ai, they all got wrong and Hallucination!

**[GoPenAI](https://daily.dev/sources/gopenai)** · 1 min read · 1 upvotes · 2 comments

## Summary

Multiple AI models, including GPT-4, Claude-2, and Perplexity.ai, incorrectly answered a three-digit multiplication question. The correct answer is 987 * 897 = 885339.

## Full article

daily.dev links to this article rather than hosting it. Read it at the original source: <https://blog.gopenai.com/987-897-ask-gpt-4-claude-2-and-perplexity-ai-they-all-got-wrong-and-hallucination-00812d0f09d1?source=rss----7adf3c3694ff---4>

## Community discussion

Top comments from developers on daily.dev.

**@coin\_spark** · 0 upvotes

> Wow, i am really curious of why the AI cant do a simple math calculation. I have asked it, here is the response from GPT-4:
>
> As an AI, I don't "think" or process errors the same way humans do. The error in the multiplication was not due to a logical thought process, but rather it was a mistake in the output I provided. My responses are generated based on patterns in data and sometimes, despite the high accuracy of the model, incorrect information can be given due to a variety of factors including how the input question is interpreted or a rare lapse in the model's reliability.
>
> In this case,...

**@alwaisy** · 0 upvotes

> ![ai-calculator-test-v1](https://res.cloudinary.com/daily-now/image/upload/s--k6Z4SmMs--/f_auto,q_auto/v1698343414/ugc/content_75ed1d0d-afb6-4288-9aef-1ea1391ed79d)
>
> From calculator is 885339

## Similar posts on daily.dev

- [Don’t just attend KubeCon \+ CloudNativeCon, Merge Forward your experience\!](https://daily.dev/posts/don-t-just-attend-kubecon-cloudnativecon-merge-forward-your-experience--l0rpp73x8) · CNCF · 0 upvotes · 0 comments
- [Announcing H2 2026 KCDs](https://daily.dev/posts/announcing-h2-2026-kcds-m96goajm1) · CNCF · 1 upvotes · 0 comments
- [Two months of Open Community Groups](https://daily.dev/posts/two-months-of-open-community-groups-asf52zhbs) · CNCF · 0 upvotes · 0 comments

---

Tags: [#ai](https://daily.dev/tags/ai), [#machine-learning](https://daily.dev/tags/machine-learning), [#math](https://daily.dev/tags/math), [#llm](https://daily.dev/tags/llm), [#gpt](https://daily.dev/tags/gpt)

[View this post on daily.dev](https://daily.dev/posts/987-897-ask-gpt-4-claude-2-and-perplexity-ai-they-all-got-wrong-and-hallucination--w8d6ow5y6)