Re:ChatGPT's image generator can be manipulated to produce v...
by anematode on Wednesday June 17, 2026 @09:27PM
(#48579391)
This is far too simplistic. Some things just don't belong in the training data. Along similar lines, Grok was found to generate images of child sexual abuse: https://www.bbc.com/news/articles/cvg1mzlryxeo
[ Parent
| on HN ]
Re:ChatGPT's image generator can be manipulated to produce v...
by HadizDulcie on Sunday June 21, 2026 @03:56AM
(#48616653)
The BBC has reported on this one too: https://www.bbc.com/news/articles/c802ldjdklzo