top
ChatGPT can be made to generate sexualised and violent images, researchers find
Key takeaways
- A redacted image created by Mindgard after Open AI said it had addessed the prompt.
- British AI security startup Mindgard figured out how to make Chat GPT create graphic pictures by slightly altering a widely-shared instruction, or prompt, which was originally designed to produce humorous results.
- After being contacted by the BBC, ChatGPT's maker OpenAI said it had taken action to stop the chatbot responding with those types of images.
Why this matters: a developing story that could shape the day's news cycle.
Chris Vallance Technology reporter Mindgard. A redacted image created by Mindgard after Open AI said it had addessed the prompt. The latest public version of Chat GPT can be made to generate sexualised images or depict scenes of graphic violence with a simple prompt, researchers have told the BBC.
British AI security startup Mindgard figured out how to make Chat GPT create graphic pictures by slightly altering a widely-shared instruction, or prompt, which was originally designed to produce humorous results.
After being contacted by the BBC, ChatGPT's maker OpenAI said it had taken action to stop the chatbot responding with those types of images.
Article preview — originally published by BBC News. Full story at the source.
Read full story on BBC News →
More top stories
Aggregated and edited by the Scoop newsroom. We surface news from BBC News alongside other reporting so you can compare coverage in one place.
Editorial policy · Corrections · About Scoop