# Experiments & Case Studies **URL:** https://humanizeaiforum.com/c/experiments-case-studies/12.md [Latest](https://humanizeaiforum.com/latest.md) · [Categories](https://humanizeaiforum.com/categories.md) · [Tags](https://humanizeaiforum.com/tags.md) --- ## [About the Experiments & Case Studies category](https://humanizeaiforum.com/t/about-the-experiments-case-studies-category/17)
**Author:** [@AndreaSoucy](https://humanizeaiforum.com/u/AndreaSoucy)\ **Replies:** 0\ **Last updated:** [December 24, 2025, 6:30pm UTC](https://humanizeaiforum.com/t/about-the-experiments-case-studies-category/17 "2025-12-24T18:30:15Z")
About the Experiments & Case Studies Category Post your results, real-world applications, and test cases using AI detection tools. Whether successful or failed, all experiments are welcome here. Why use this category… --- ## [Best AI content detector for academic writing. My testing notes](https://humanizeaiforum.com/t/best-ai-content-detector-for-academic-writing-my-testing-notes/145)
**Author:** [@codewrath58](https://humanizeaiforum.com/u/codewrath58)\ **Replies:** 6\ **Last updated:** [September 23, 2026, 2:30pm UTC](https://humanizeaiforum.com/t/best-ai-content-detector-for-academic-writing-my-testing-notes/145 "2026-09-23T14:30:01Z")
Running a comparison over the last six weeks for a piece I’m writing on AI tools in graduate education. Tested five detectors on the same set of documents: a mix of confirmed AI-generated text, human-written academic pro… --- ## [Tested four AI image detectors on 30 images. Here is what the numbers showed](https://humanizeaiforum.com/t/tested-four-ai-image-detectors-on-30-images-here-is-what-the-numbers-showed/215)
**Author:** [@Appartement](https://humanizeaiforum.com/u/Appartement)\ **Replies:** 5\ **Last updated:** [September 22, 2026, 8:48am UTC](https://humanizeaiforum.com/t/tested-four-ai-image-detectors-on-30-images-here-is-what-the-numbers-showed/215 "2026-09-22T08:48:29Z")
tested four AI image detectors on 30 images. here is what the numbers showed. 20 AI-generated images across different models and styles. 10 human-created images in styles that overlap with common AI aesthetics (digital … --- ## [AI transcription on a meeting with five non-native speakers: what the accuracy looked like](https://humanizeaiforum.com/t/ai-transcription-on-a-meeting-with-five-non-native-speakers-what-the-accuracy-looked-like/214)
**Author:** [@thomas.seeker](https://humanizeaiforum.com/u/thomas.seeker)\ **Replies:** 5\ **Last updated:** [September 21, 2026, 5:56am UTC](https://humanizeaiforum.com/t/ai-transcription-on-a-meeting-with-five-non-native-speakers-what-the-accuracy-looked-like/214 "2026-09-21T05:56:29Z")
AI transcription on a meeting with five non-native speakers: what the accuracy looked like. ran an experiment on our last all-hands. five out of eight people speaking had English as a second language. different first la… --- ## [Ran the same paragraph through six detectors. The disagreement was not small](https://humanizeaiforum.com/t/ran-the-same-paragraph-through-six-detectors-the-disagreement-was-not-small/216)
**Author:** [@tallest.tower.2016](https://humanizeaiforum.com/u/tallest.tower.2016)\ **Replies:** 5\ **Last updated:** [September 20, 2026, 3:12pm UTC](https://humanizeaiforum.com/t/ran-the-same-paragraph-through-six-detectors-the-disagreement-was-not-small/216 "2026-09-20T15:12:30Z")
ran the same paragraph through six AI detectors and the disagreement was not small. sharing the results because I couldn’t find a systematic comparison when I was looking for one. the paragraph: a methodology section fr… --- ## [I tested how to reduce AI detection score in my writing -- here's what actually moved the needle](https://humanizeaiforum.com/t/i-tested-how-to-reduce-ai-detection-score-in-my-writing-heres-what-actually-moved-the-needle/98)
**Author:** [@MrDoubtfire](https://humanizeaiforum.com/u/MrDoubtfire)\ **Replies:** 9\ **Last updated:** [September 18, 2026, 6:14pm UTC](https://humanizeaiforum.com/t/i-tested-how-to-reduce-ai-detection-score-in-my-writing-heres-what-actually-moved-the-needle/98 "2026-09-18T18:14:06Z")
i want to be clear about what this is and isn’t. this is not a thread about gaming a system. it’s a record of what editing changes actually affected detection scores on my own content, with the goal of understanding what… --- ## [Case study: testing three free AI detectors for classroom use](https://humanizeaiforum.com/t/case-study-testing-three-free-ai-detectors-for-classroom-use/156)
**Author:** [@Pumpkinavigation](https://humanizeaiforum.com/u/Pumpkinavigation)\ **Replies:** 5\ **Last updated:** [July 4, 2026, 8:04pm UTC](https://humanizeaiforum.com/t/case-study-testing-three-free-ai-detectors-for-classroom-use/156 "2026-07-04T20:04:29Z")
I’ve been running an informal test over the past two months because I couldn’t justify paying for a detection tool out of pocket and wanted to know whether the free options were worth bothering with at all. Not a rigorou… --- ## [How I rewrote an AI draft until it actually sounded like me -- a rough case study](https://humanizeaiforum.com/t/how-i-rewrote-an-ai-draft-until-it-actually-sounded-like-me-a-rough-case-study/86)
**Author:** [@AlfioRo88](https://humanizeaiforum.com/u/AlfioRo88)\ **Replies:** 5\ **Last updated:** [March 21, 2026, 4:04pm UTC](https://humanizeaiforum.com/t/how-i-rewrote-an-ai-draft-until-it-actually-sounded-like-me-a-rough-case-study/86 "2026-03-21T16:04:32Z")
i want to share a specific example from last month because i think it’s more useful than general advice. i’m a fiction writer and writing coach. i use AI for first-draft material sometimes – mostly for scenes i’m stuck … --- ## [Blind Test With Faculty Panel: 5 Human Essays vs 5 ChatGPT Essays — Could We Reliably Tell Before Checking Originality.ai?](https://humanizeaiforum.com/t/blind-test-with-faculty-panel-5-human-essays-vs-5-chatgpt-essays-could-we-reliably-tell-before-checking-originality-ai/62)
**Author:** [@ErnestPrice](https://humanizeaiforum.com/u/ErnestPrice)\ **Replies:** 6\ **Last updated:** [March 6, 2026, 1:27am UTC](https://humanizeaiforum.com/t/blind-test-with-faculty-panel-5-human-essays-vs-5-chatgpt-essays-could-we-reliably-tell-before-checking-originality-ai/62 "2026-03-06T01:27:07Z")
We ran a small internal experiment last month. Ten short argumentative essays. Five written by actual undergraduates. Five generated using ChatGPT from the same prompts. We removed names, formatted everything identic… --- ## [AI detection is becoming a credibility test](https://humanizeaiforum.com/t/ai-detection-is-becoming-a-credibility-test/46)
**Author:** [@penhillcurrant](https://humanizeaiforum.com/u/penhillcurrant)\ **Replies:** 2\ **Last updated:** [January 29, 2026, 4:27pm UTC](https://humanizeaiforum.com/t/ai-detection-is-becoming-a-credibility-test/46 "2026-01-29T16:27:29Z")
We’ve been running controlled experiments with AI-assisted content across thought leadership, case studies, and sales enablement—same briefs, same editors, different workflows. The result that surprised most people inte…