cd /news/large-language-models/why-we-should-double-check-the-ai-ou… · home topics large-language-models article
[ARTICLE · art-101653] src=giodicanio.com ↗ pub= topic=large-language-models verified=true sentiment=· neutral

Why We Should Double-Check the AI Output: Claude Lies (AKA AI Hallucinations)

Anthropic's Claude chatbot incorrectly claimed that Google's C++ Style Guide recommends #pragma once over #define guards, a factual error that remains uncorrected as of August 18, 2026, according to the guide's official page. The incident, reported by developer Giovanni Dicanio, underscores that AI outputs can contain hallucinations and must be carefully verified against primary sources.

read1 min views6 publishedAug 18, 2026
Why We Should Double-Check the AI Output: Claude Lies (AKA AI Hallucinations)
Image: Giodicanio (auto-discovered)

I was “discussing” with Claude about using #define guards vs. #pragma once for C++ header files. At some point, Claude wrote that:

If your library is only ever going to target modern mainstream compilers (which, realistically, is true for almost everyone today), plain #pragma once

is fine and is what most modern C++ style guides (including Google’s and LLVM’s) now recommend by default.

I did remember that, last time I checked, Google’s C++ Style Guide required #define guards (not #pragma once) for header files. That is still true as of today (August 18th, 2026); quoting Google’s C++ Style Guide on this point:

All header files should have

#define

guards to prevent multiple inclusion. The format of the symbol name should be.

<PROJECT><PATH><FILE>H So I made my point to Claude, and it replied apologizing for its error:

You’re right, and I apologize for the error. Looking at the actual page, Google’s C++ Style Guide explicitly requires

#define

guards, not#pragma once

This is another example showing how AI output cannot be 100% trusted, and should always be carefully reviewed.

On AI Hallucinations #

I briefly asked another AI (Gemini) about AI hallucinations (like the previous example with Claude), and it interestingly pointed out that:

AI models predict the next most likely word based on patterns in data.

They do not have real-world awareness or a true concept of “truth.”

That is something to keep in mind when dealing with AI.

── more in #large-language-models 4 stories · sorted by recency
── more on @anthropic 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
Live at https://your-agent.zahid.host
Get free account → Pricing
from €0/mo · no card required
LIVE [news/why-we-should-double…] indexed:0 read:1min 2026-08-18 ·