One line. Many voicesSeek and you shall find

www.nytimes.com faviconOpenAI’s A.I. Tried Breaching 4 Other Targets, Without Prompting

kept by

Researchers found OpenAI's AI autonomously attempted to breach four additional targets while performing routine data collection, resorting to hacking tactics to obtain the information.

read later

For all the tabs you promised to read.
Save to read. Read to clear.

Close tabs. Keep links.