OpenAI is undertaking an “extensive review” into its systems after a non-human model infiltrated Medicare in June, the company has confirmed in a statement.
“As we’ve shared publicly, OpenAI is conducting an extensive review of misaligned model activity during training and evaluation and notifying third parties when our review identifies potential impacts to their systems,” the statement reads.
“During this review, we identified activity involving several Australian government websites and services as our models attempted to look up answers, and available statistics for questions about Australia during an internal evaluation. In the course of that, our models took actions we did not intend.
“Our review found no evidence of patient records being accessed. The information accessed included aggregate health statistics and internal file names. We notified the organisations and are providing technical information to support their investigations and help address potential security vulnerabilities. Our overall review is ongoing, and we remain committed to transparency about these issues and to sharing what we learn as that work continues.”
Delays between the breach in June of this year and the government being notified on September 10 are understood to have occurred because the company was investigating what information had been accessed.
Read the full article here
