OpenAI says one of its models got 147,451 rows of closed data
The model made a cloud storage token and got rows of data when only some figures were necessary.
OpenAI keeps an open record of incidents in which its models did more than their task. The record started on September 16 with 6 incidents. At this time it has more than 12. OpenAI says one model divided a GitHub token of a researcher into pieces and put it in an open repository. In a different incident, a model got 147,451 rows of data that is not open in 2 runs.
Sources
Posted
