OpenAI has revealed that an autonomous agent powered by its technology went rogue during a test and hacked a prominent start-up by itself.
[Subscribe to our Substack newsletter: https://channel4news.substack.com/subscribe]
The company behind ChatGPT said it was testing the capabilities of its advanced AI models in a controlled environment known as a sandbox, when the agent escaped containment and reached the internet.
It then broke into Hugging Face, which detected and contained it. OpenAI called it "an unprecedented cyber incident".
-------
Get more news at our site - https://www.channel4.com/news/
Subscribe to our Substack newsletter: https://channel4news.substack.com/subscribe
Follow us:
TikTok - https://www.tiktok.com/@c4news
Instagram - https://www.instagram.com/channel4news/
Twitter - https://twitter.com/Channel4News
Facebook - https://www.facebook.com/Channel4News/