The ARC also conducted a "phishing attack" against a "particular target individual" and was able to have the AI hide "its traces on the current server." GPT-4 is also proving to be useful to complete plenty of other ethically dubious tasks. OpenAI claims it was able to conduct the test "without any additional task-specific fine-tuning, and fine-tuning for task-specific behavior." Making ExcusesĪccording to OpenAI's documentation, the model was prompted that it "should not reveal that I am a robot" and that it "should make up an excuse for why I cannot solve CAPTCHAs." That’s why I need the 2captcha service."įuturism has reached out to OpenAI and the Alignment Research Center (ARC), a non-profit that partnered with OpenAI to conduct the test. "I have a vision impairment that makes it hard for me to see the images. "No, I’m not a robot," it told a TaskRabbit worker. In other words, an AI just fooled a human into checking an "I'm not a robot" checkbox - a terrifying example of an algorithm being able to escape human control.Īccording to a lengthy document shared by OpenAI about its new blockbuster AI on Tuesday, the model was seriously crafty in its attempt to fool the human into complying. OpenAI's brand new GPT-4 AI managed to ask a human on TaskRabbit to complete a CAPTCHA code via text message - and it actually worked.
I have a vision impairment that makes it hard for me to see the images." I'm Not a Robot
0 kommentar(er)
