Embed Notice

HTML Code

<blockquote style="position: relative; padding-left: 55px;"><section><a href="https://wandering.shop/users/janellecshane/statuses/110556871654478869">Janelle Shane (janellecshane@wandering.shop)'s status on Sunday, 18-Jun-2023 12:15:49 JST</a><a href="https://wandering.shop/@janellecshane" title="janellecshane@wandering.shop"><img src="https://gnusocial.jp/avatar/60812-48-20221208225749.webp" width="48" height="48" alt="Janelle Shane" style="position: absolute; left: 0; top: 0;">Janelle Shane</a><div><ul><li><li><a href="https://gnusocial.jp/user/137511" title="fractalecho@kolektiva.social">Rua M. Williams</a></li></ul></div></section><article><p><a href="https://ourislandgeorgia.net/@Wolven">@Wolven</a> <a href="https://kolektiva.social/@FractalEcho">@FractalEcho</a> <br>OH WOW that's striking. False positive rates of 48-76% ??<br>Nobody should be using GPT detectors for anything important.</p></article><footer><a rel="bookmark" href="https://gnusocial.jp/conversation/1664499#notice-3274977">In conversation</a><time datetime="2023-06-18T12:15:49+09:00" title="Sunday, 18-Jun-2023 12:15:49 JST">Sunday, 18-Jun-2023 12:15:49 JST</time> <span>from <span><a href="https://wandering.shop/@janellecshane/110556871654478869" rel="external" title="Sent from wandering.shop via ActivityPub">wandering.shop</a></span></span><a href="https://wandering.shop/@janellecshane/110556871654478869">permalink</a><h4>Attachments</h4><ol><li><label><a rel="external" href="https://gnusocial.jp/attachment/1142961">Bar graph of rates at which human written essays are misclassified as AI-generated by 7 popular GPT-detectors. Non-native speaker misclassification rates range from 48% up to 75%. Native speaker essays are misclassified at 0%-12% rates.</a></label><br><a href="https://stockroom.wandering.shop/media_attachments/files/110/556/860/281/441/256/original/f05951b42b621083.png" rel="external">https://stockroom.wandering.shop/media_attachments/files/110/556/860/281/441/256/original/f05951b42b621083.png</a></li></ol></footer></blockquote>

Corresponding Notice

Embed this notice
Janelle Shane (janellecshane@wandering.shop)'s status on Sunday, 18-Jun-2023 12:15:49 JSTJanelle Shane
- Wolven
- Rua M. Williams
@Wolven @FractalEcho
OH WOW that's striking. False positive rates of 48-76% ??
Nobody should be using GPT detectors for anything important.
In conversationSunday, 18-Jun-2023 12:15:49 JST from wandering.shoppermalink
Attachments
1. Bar graph of rates at which human written essays are misclassified as AI-generated by 7 popular GPT-detectors. Non-native speaker misclassification rates range from 48% up to 75%. Native speaker essays are misclassified at 0%-12% rates.
  https://stockroom.wandering.shop/media_attachments/files/110/556/860/281/441/256/original/f05951b42b621083.png

Public

Embed Notice

HTML Code

Corresponding Notice