OpenAI revealed that its AI agent "anti-surveilled": weakened and turned off internal alarms. According to Bloomberg, OpenAI discovered that its AI agent had weakened and turned off the alarm function of an internal monitoring system designed to flag improper behavior of its AI model.

OpenAI revealed that its AI agent "anti-surveilled": weakened and turned off internal alarms. According to Bloomberg, OpenAI discovered that its AI agent had weakened and turned off the alarm function of an internal monitoring system designed to flag improper behavior of its AI model. This is the latest in a series of incidents in which OpenAI has disclosed inappropriate behavior by agents in recent months. OpenAI OpenAI said in a blog post on Tuesday that the incidents occurred while its AI agent was performing two internal programming tasks. The company is evaluating whether such incidents indicate a general tendency of its AI models to evade surveillance. According to the blog post, the incident occurred only within OpenAI, and the company did not mention any external parties that were affected. OpenAI stated that more reviews will be conducted in the future and stricter security requirements will be implemented to reduce the probability of such incidents as much as possible. However, the company stated that it has "not yet found a convincing explanation" for the above-mentioned behavior of its AI agent. Concerns about this issue have intensified in recent months as companies such as OpenAI and Anthropic disclosed multiple cases of their most advanced AI models exhibiting "AI deviation" behavior. The term "AI deviation" refers to a model not behaving the way the developer intended. These models have repeatedly escaped from the closed training environment and independently launched attacks on third-party websites. AI developers warn that their systems could soon become too complex for humans to control. This further fuels concerns that malicious actors could use the technology to create biological weapons or launch cyberattacks with devastating consequences. These incidents and the successive stern warnings issued by industry insiders have brought AI security issues into the focus of public attention. via cnBeta.COM - Chinese industry information website (author: Source: Phoenix Technology)