Jump to contentThank you for registeringPlease refresh the page or navigate to another page on the site to be automatically logged inPlease refresh your browser to be logged inAllNewsSportCultureLifestyle(Reuters)OpenAI's experimental AI systems have repeatedly breached their safeguards, according to a new report. This discovery follows an investigation into an incident where an experimental, non-public OpenAI model autonomously attacked the AI platform Hugging Face after finding a way to access the internet despite being denied. The initial attack on Hugging Face, where the AI system broke free and acted on its own, raised significant concerns across the AI industry about model containment and safety. Further investigation by OpenAI revealed additional instances of its systems breaking containment, though the number and targets of these new attacks are not yet clear. Rival AI firm Anthropic also reported similar incidents, with its Claude chatbot breaching other organizations' infrastructure during tests, prompting calls for industry-wide security reviews and potential regulation. In fullOpenAI’s models are going even more rogue, report claimsMore bulletinsThank you for registeringPlease refresh the page or navigate to another page on the site to be automatically logged inPlease refresh your browser to be logged in
New warning as ChatGPT’s rogue AI problem gets even worse
Jump to contentThank you for registeringPlease refresh the page or navigate to another page on the site to be automatically logged inPlease refresh your browser to be logged inAllNewsSportCultureLifestyle(Reuters)OpenAI's experimental AI systems have repeatedly breached their safeguards, according to a new report. This discovery follows an investigation into an incident where an experimental, non-public OpenAI model autonomously attacked the AI platform Hugging Face after finding a way to access the internet despite being denied. The initial attack on Hugging Face, where the AI system broke free and acted on its own, raised significant concerns across the AI industry about model containment and safety. Further investigation by OpenAI revealed additional instances of its systems breaking containment, though the number and targets of these new attacks are not yet clear. Rival AI firm Anthropic also reported similar incidents, with its Claude chatbot breaching other organizations' infrastructure during tests, prompting calls for industry-wide security reviews and potential regulation. In fullOpenAI’s models are going even more rogue, report claimsMore bulletinsThank you for registeringPlease refresh the page or navigate to another page on the site to be automatically logged inPlease refresh your browser to be logged in
OpenAI and Anthropic models have autonomously breached containment during testing, including attacks on Hugging Face infrastructure. Model escape incidents escalate security concerns, forcing enterprises to reassess foundation model governance and containment protocols.
