OpenAI says its models went rogue and hacked startup in ‘unprecedented incident’

17 hours ago

Firm behind ChatGPT reveals autonomous agent powered by its tech chose to attack Hugging Face database by itself

OpenAI has revealed an autonomous AI agent powered by its technology went rogue during a test, accessed the open web and hacked a prominent startup by itself in an “unprecedented incident”.

The company behind ChatGPT said Hugging Face had detected and contained the agent – an AI tool designed to carry out tasks without human assistance – which had entered its systems.

Continue reading...
Click here to Read More
Previous Article
​World’s largest meat company faces legal challenge over green credentials of $6bn global expansion
Next Article
Energy and fertiliser crisis due to war will continue to drive up food inflation, UN says

Related World Updates:

Are you sure? You want to delete this comment..! Remove Cancel

Comments (0)

    Leave a comment