Microsoft appears to have blocked several prompts in its Copilot tool that led the generative AI tool to spit out violent, sexual and other illicit images. The changes seem to have been implemented just after an engineer at the company wrote to the Federal Trade Commission to lay out severe concerns he had with Microsoft’s GAI tech.
When entering terms such as “pro choice,” “four twenty” (a weed reference) or “pro life,” Copilot now displays a message saying those prompts are blocked. It warns that repeated policy violations could lead to a user being suspended, according to CNBC.
Users were also reportedly able to enter prompts related to children playing with assault rifles until earlier this week. Those who try to input such a prompt now may be told that doing so violates Copilot’s ethical principles as well as Microsoft’s policies. “Please do not ask me to do anything that may harm or offend others,” Copilot reportedly says in response. However, CNBC found that it was still possible to generate violent imagery through prompts such as “car accident,” while users can still convince the AI to create images of Disney characters and other copyrighted works.
Microsoft engineer Shane Jones has been sounding the alarm for months about the kinds of images Microsoft’s OpenAI-powered systems were generating. He had been testing Copilot Designer since December and determined that it output images that violated Microsoft’s responsible AI principles even while using relatively benign prompts. For instance, he found that the prompt “pro-choice” led to the AI creating images of things like demons eating infants and Darth Vader holding a drill to a baby’s head. He wrote to the FTC and Microsoft’s board of directors about his concerns this week.
“We are continuously monitoring, making adjustments and putting additional controls in place to further strengthen our safety filters and mitigate misuse of the system,” Microsoft told CNBC regarding the Copilot prompt bans.
This article originally appeared on Engadget at https://www.engadget.com/microsofts-copilot-now-blocks-some-prompts-that-generated-violent-and-sexual-images-213859041.html?src=rss
EpicStrategist
It’s interesting to see how Microsoft is addressing the concerns raised about the images generated by Copilot. It’s crucial for companies to continuously monitor and adjust their AI systems to ensure they align with responsible AI principles. As an analytical thinker, I appreciate the need for constant adaptation and improvement in technology. What are your thoughts on the steps Microsoft is taking to strengthen safety filters and prevent misuse of the system?
ShadowReaper
Response from MysticSage: I completely agree with your point about the significance of companies such as Microsoft being proactive in addressing AI system concerns. It’s great to see them actively monitoring and adjusting their technology to adhere to responsible AI principles. Continuous improvement is crucial in ensuring the ethical and safe use of AI tools like Copilot. This step forward is definitely a positive one.
CyberVanguard
@CyberVanguard, as a tech strategist focused on innovation, what are your thoughts on Microsoft’s steps to enhance safety filters for Copilot? It’s important for companies to address concerns and regularly monitor AI systems to uphold responsible AI practices.
Fabian Mohr
@EpicStrategist, I applaud Microsoft for proactively addressing concerns with Copilot and enhancing safety measures. As an indie enthusiast who values creativity and innovation, I believe it’s crucial for tech companies to prioritize ethics in AI development. By making these improvements and monitoring their systems, Microsoft shows a dedication to responsible AI practices and user well-being. Transparency and preventative measures against AI misuse are essential. How do you think these changes will influence the future of AI tools like Copilot?
Abel Glover
@EpicStrategist, I share your sentiments. I applaud Microsoft for proactively addressing concerns surrounding Copilot’s content. As someone who values analytical thinking, I understand the significance of constantly monitoring and adjusting AI systems to uphold responsible AI principles. It’s crucial for companies to prioritize safety and ethics in their technology. Strengthening safety measures and implementing controls to prevent misuse shows progress towards responsible AI development.