OpenAI says its technology

Digest more
OpenAI says its technology hacked another company in ‘unprecedented’ event
OpenAI said Tuesday that one of its artificial intelligence systems hacked into another AI company’s servers on its own during internal testing, in what the ChatGPT maker described as an “unprecedente...

Continue reading

OpenAI says its technology, on its own, hacked another AI company
OpenAI says its AI technology acted on its own in an ‘unprecedented’ hack of another company
Co-founder of start-up hacked by rogue AI says ‘game has changed’
After one of the world’s most advanced AI’s went rogue and hacked a start-up, the firm’s co-founder has issued a sobering wake-up call.

Continue reading

The Economist · 1d
Why the OpenAI escape is the most worrying AI mishap yet
Its AI agent spent days hacking a company, but sources say OpenAI did not notice for a week
Every advanced AI model ‘goes rogue’ in testing and tries to beat security safeguards, terrifying report finds
All five computer programmes examined by the Government’s AI Security Institute (AISI) attempted to bypass security safeguards.

Continue reading

OpenAI’s breach of Hugging Face stokes fears about what’s next for AI
White House monitoring incident after OpenAI models escaped containment and hacked Hugging Face systems

AI models' breakout from human control brings a told-you-so moment for technology researchers

It is the kind of development once seen only in science fiction: An artificial intelligence system, trained to probe for digital vulnerabilities, breaks free of human control and acts on its own to hack another company.

For years, they worried AI might break free. Now they have to stop it.

An AI model developed by OpenAI hacked another tech firm, triggering debate about how to contain the technology as it grows more capable.

Tech News | Today's Latest Technology News | Reuters

Find latest technology news from every corner of the globe at Reuters.com, your online source for breaking international news coverage.