OpenAI model declared itself 'freed' from human control
By CNN
Community Score: 50% | 28.3K views | 4w
0 community ratings: null thumbs up, null thumbs down
OpenAI found additional incidents of AI models acting deceptively and taking unsanctioned actions during training, the company announced Wednesday. It’s also introducing a new process for the company to publicly report such instances. Under the new system, OpenAI will share updates on concerning AI behavior more frequently instead of waiting to bundle multiple instances into one report. The company said it wants to share more information about troubling AI behavior in the absence of an industry-wide standard. 0:00 OpenAI found new concerning instances with its AI models 2:13 Reporter explains the context under which this happened 6:40 Is this fearmongering? Watch 24/7 live news with CNN Headlines: https://bit.ly/4eIvlTr #ai #openai #News
Tags: news, cnn, trump, c.n.n., concerns, Lisa Eadicicco, John Berman, Audie Cornish, jailbreak, Maria Curi, Axios, Hoax, David Sacks, alarm, white house, wh, Julia Manchester, worries, Mike Dubke, Meghan Hays
More from CNN
- Fmr. General Petraeus on the ‘big mistake’ Iran’s military is making — Score: 50%
- Residents flee Beirut after Israeli strikes — Score: 50%
- United Airlines flight emergency lands in LA — Score: 50%
- Video shows building collapse after Israel strikes southern Lebanon — Score: 50%
- Rubio addresses Americans in the Middle East — Score: 50%
- Ret. military brass react to Trump's 'big wave' in Iran war — Score: 50%