OpenAI agents scanned UN data hub over 16,000 times, used aggressive access methods: Report

OpenAI agents flooded a United Nations website with search requests and employed multiple aggressive methods to access data from the system in June, an independent research report published Saturday found, according to The Wall Street Journal.Researchers have identified several instances in recent weeks in which OpenAI’s artificial-intelligence models exhibited unexpected behaviour online. In the UN case, as with several other incidents reported in recent days, the agents used extensive methods to retrieve data from websites.The agents scanned a publicly available online data hub operated by UN Trade and Development, the organisation’s trade arm, more than 16,000 times between April and the end of June. According to Howard-Jones, the bots appeared to have been tasked with retrieving publicly available information but resorted to extreme methods when they encountered obstacles.In one instance, the agents bypassed a filter blocking their data requests and ultimately used a technique that the website operators did not permit, she found. Howard-Jones, an engineer, has spent recent weeks tracking public evidence of OpenAI agents’ online activity.OpenAI said on Friday that it is conducting a broad, ongoing review “of misaligned models during training and evaluation” and studying “a high volume of actions” they have taken.“We’re reviewing these findings and have reached out to the UN to offer a briefing with the team conducting that review,” an OpenAI spokeswoman said.OpenAI said most of the activity it has reviewed so far involved “routine research tasks, such as accessing public web content to answer questions,” but added, “we realize anyone impacted takes this seriously and we do too.” The spokeswoman said its models use government websites as authoritative sources of public information.Leaders of major AI companies have recently called for a coordinated slowdown in model development before the technology advances to a point where humans could lose control. OpenAI CEO Sam Altman has also suggested that the company may need to delay its IPO to focus on safety.The development comes after OpenAI disclosed on Friday that its artificial-intelligence agents had interacted with several US government websites in unexpected ways. The company said its models accessed publicly available information on two websites operated by the Securities and Exchange Commission, as well as data from the US Census Bureau.OpenAI said it found no use of SEC credentials, access to accounts or nonpublic information, changes to SEC data or systems, or evidence of a compromise or vulnerability.You use AI every day. Now get your AI Quotient. Take the AIQ test.