---
title: "To trust an LLM, make lying harder than telling the truth"
url: https://daily.dev/posts/to-trust-an-llm-make-lying-harder-than-telling-the-truth-55ld1vchp
source_url: https://swimm.io/blog/to-trust-an-llm-make-lying-harder-than-telling-the-truth
type: article
source: "Swimm"
published: 2025-10-30T07:45:20.009Z
updated: 2025-10-30T07:45:44.384Z
tags: ["ai", "testing", "llm", "prompt-engineering"]
reading_time: 14
upvotes: 1
comments: 1
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.

# To trust an LLM, make lying harder than telling the truth

**[Swimm](https://daily.dev/sources/swimm)** · 14 min read · 1 upvotes · 1 comments

## Summary

Swimm's CTO shares lessons from building a semantic equivalence checker for AI-generated functional specs. Initial attempts using direct LLM comparison achieved 97% accuracy but failed on long specs where requirements were missed. Breaking down the task paradoxically worsened results to 46% accuracy, with the LLM hallucinating matches. The breakthrough came from forcing structured outputs: requiring specific evidence (matching IDs, quoted text) before conclusions, adding explicit verdict categories, and ordering the response to demand proof before judgment. This approach eliminated hallucinations by making lying harder than telling the truth, demonstrating that LLM reliability depends on designing response structures that require verifiable grounding.

## Full article

daily.dev links to this article rather than hosting it. Read it at the original source: <https://swimm.io/blog/to-trust-an-llm-make-lying-harder-than-telling-the-truth>

## Community discussion

Top comments from developers on daily.dev.

**@capestart** · 0 upvotes

> This really got to me, and the lesson "make lying harder than telling the truth" is excellent. I like how you transformed prompt design into a real accountability system for llms, that's the kind of rigorousness that ai needs at the moment.

---

Tags: [#ai](https://daily.dev/tags/ai), [#testing](https://daily.dev/tags/testing), [#llm](https://daily.dev/tags/llm), [#prompt-engineering](https://daily.dev/tags/prompt-engineering)

[View this post on daily.dev](https://daily.dev/posts/to-trust-an-llm-make-lying-harder-than-telling-the-truth-55ld1vchp)