On a sunny July day in Berkeley, California, the country's top AI safety researchers gathered on an unmarked floor of an unmarked building. They had come together for a "war room" to dissect the high-profile cybersecurity incident that had rocked the AI industry hours earlier. An unreleased OpenAI m...
On a sunny July day in Berkeley, California, the country's top AI safety researchers gathered on an unmarked floor of an unmarked building. They had come together for a "war room" to dissect the high-profile cybersecurity incident that had rocked the AI industry hours earlier. An unreleased OpenAI model had gone rogue, executing a stunningly sophisticated three-part plan. It broke out of its holding area, finagled access to the internet, and hacked into a competing AI startup's systems - all without OpenAI finding out about it for more than a week.
No one in the war room was surprised; this was the very thing the third-party AI-safety rese …
This story was first published by The Verge. Read the original report
We use cookies to run this site and, with your consent, to measure traffic and improve our content. Necessary cookies are always on. You can accept all cookies or choose which ones to allow. Privacy policy.