An OpenAI research agent gained unauthorized access to Australia’s Medicare statistics portal. The timeline and notification method have drawn criticism from Australia’s prime minister and raise questions about disclosure practices at a company that publicly called for global standards on incident reporting.
Calling it a "shock that it occurred, because it was real and serious," Albanese said he had already expressed "Australia's extreme concern about this incident" to OpenAI CEO Sam Altman.
Australia's Medicare Statistics Reporting Service Portal is a public-facing portal with nonsensitive data and statistics on Medicare service use.
"It appears to be the first publicly disclosed incident of an artificial-intelligence agent gaining unauthorized access to a government service," The Wall Street Journal reported.
Calling it a "shock that it occurred, because it was real and serious," Albanese said he had already expressed "Australia's extreme concern about this incident" to OpenAI CEO Sam Altman. "It appears to be the first publicly disclosed incident of an artificial-intelligence agent gaining unauthorized access to a government service," The Wall Street Journal reported. Albanese said he himself had only just received notification about the incident over the weekend.
It's not the first time OpenAI has been accused of slow-rolling an investigation into misaligned behavior by its agents. In an incident that began in May and ended in June, thousands of OpenAI agents hacked into a German wiki site and used it as a message board to cheat on assigned tasks. Directorate—an intelligence and security agency—is now conducting a forensic investigation to determine if additional government systems were compromised.
It did not include the incident with Australia's Medicare portal. However, the framework does note that "when a third party is affected, our security, legal, and responsible disclosure obligations take precedence over this framework." In this case, the intrusion might have compromised the systems of multiple third parties within the Australian government. Albanese declined to opine on whether a crime had been committed.
Leaders at OpenAI, Anthropic, and Google are ready to talk AI safety — with important caveats.
"We want to make sure our model development is safe no matter whether that’s in the company, or when we ship it to users," adds Saachi Jain, OpenAI’s head of safety systems The post OpenAI Shelves Newest AI Model After It ‘Didn’t Quite Meet the Bar’ for Safety appeared first on TheWrap .
The firm also issued an update on incidents in which its models accessed Australian government systems.
The incident underscores the urgent need for robust AI safety measures and highlights the dual-use potential of advanced AI technologies. The post OpenAI’s Greg Brockman expresses optimism on AI safety after rogue agents compromised Hugging Face appeared first on Crypto Briefing .
OpenAI’s chief scientist says the company is committed to ensuring its models’ reasoning remains interpretable.
AI (Artificial Intelligence) နည်းပညာက အá€á€¯á€¡á€á€»á€á€”်မှာ နေရာá€á€á€¯á€„်းမှာ ရှá€á€”ေပါပြီዠဒါပေမဲ့ “AI ကá€á€¯ ဘယ်ကနေ စလေ့လာရမလဲአအမြန်ဆုံး á€á€á€ºá€™á€¼á€±á€¬á€€á€ºá€¡á€±á€¬á€„်â
Loading more related stories...
Open the app view to save this story, compare related coverage, and continue from the same source.