HomeAI · summaries
Storia in 4 fonti
ChatGPT found to generate sexualised, violent images through simple prompts: BBC
Researchers say small changes to the prompt can still produce troubling content despite the fix
Confronto fonti
4 prospettive sulla stessa storiaTimeline cronologica
- ·
cryptobriefing.com
Researchers find ChatGPT can generate sexualized, violent images despite safety filters
Researchers document jailbreak techniques that bypass ChatGPT safety filters to generate sexualized and violent images, raising questions about AI
- ·
bdnews24.com
ChatGPT found to generate sexualised, violent images through simple prompts: BBC
Researchers say small changes to the prompt can still produce troubling content despite the fix
- ·
independent.co.uk
ChatGPT ‘can be made to generate sexualised and violent images’
Images generated by AI showed women who had been killed or sexually abused
- ·
infobae.com
ChatGPT puede generar imágenes violentas y secuales a partir de simples prompts, revela informe
El problema expone deficiencias en los sistemas de moderación de contenido de la inteligencia artificial de OpenAI