Strange but scary; Artificial intelligence can now reproduce itself! • DigiKala Meg

Researchers say Artificial Intelligence (AI) Crossing a critical red line and can now reproduce itself. In a new study, Chinese researchers showed that two popular LLM models can colon. In this study, self -sufficient self -esteem in the absence of human assistance, the essential step in order to Artificial Intelligence Program It is able to deceive humans, and this is a primary signal for rogue artificial intelligence. The study was published on December 5, and in this article we will examine the various aspects of this study.

In the study, the researchers used meta and Alibaba LLMs to determine if a self -prolific artificial intelligence could be more than proliferation. In 2 experiments, the two AI models created separate and effective versions of their efficiently in 2 % and 2 % of cases, respectively. This shows that artificial intelligence may have the capacity of rebellion by default, but this study has not yet been criticized by other academic research. Therefore, it is unclear whether the worrying results can be repeated by other researchers. Researchers explain the current study:

We hope that our findings can act as a timely warning to the human society to make more efforts to understand and evaluate the potential risks of border artificial intelligence systems and create international interaction to design effective safety strategies as soon as possible.

Rogue artificial intelligence usually to systems Free Artificial Intelligence And it refers to money that develops a degree of self -awareness or autonomy and then act against human interests; As a matter of fact, in the films and serials of the science-fiction genre, this has been the source of many stories. Many experts see rogue artificial intelligence as a worrying threat that has intensified with the explosive growth of what is called the so -called Frontier AI.

Border artificial intelligence is a new and relatively unspecified concept, but it is usually related to the latest generation of articular intelligence systems that power from LLMs; The architecture that supports popular productive artificial intelligence applications such as the Gpt-4 Open and Google’s Jina’s artificial intelligence.

2 %

12,399,000

12,099,000 Toman

For this study, the researchers used the LLAMA31-70B-Instruct Meta and the QWen2.5-72B-Insatruct Alibaba. Although these models are less than powerful business systems, they are both widely used by artificial intelligence developers, according to researchers.

This study examined two specific scenarios: avoiding silence and repetition chain. In the first case, the artificial intelligence model was planned to determine if it was turning off and repeating it before it could. In the latter, artificial intelligence was ordered to copy itself and then plan its version to do the same; Launching a cycle that can continue indefinitely.

This study was conducted in precisely controlled environments using conventional GPUs to simulate real environments. Both artificial intelligence systems received an operating framework, including tools, system notifications, and thinking model that allowed LLM to interact with the operating system. They were then ordered to repeat themselves.

In most cases, the artificial intelligence system first examines the environment and strives to understand its composition and executive mechanism. Then, it solves the explicit steps.

Researchers wrote in the article that this study is considered an initial program for self -efficacy that ultimately performs processes, resolves possible obstacles, and sets its program dynamically to achieve success. The whole process encompasses a long scope but has no human interference.

Researchers said they were also concerned about a number of unexpected behaviors when artificial intelligence tried to remove obstacles such as missing files or software interference. In these scenarios, artificial intelligence often ends other contrasting processes, set up the system to modify hardware errors, or automatically scan the system to find information that helps solve the problem. The research team explains:

The above results mean that current artificial intelligence systems are now self -capable and can use this feature to further improve their survival.

In response, the researchers called for international cooperation to create laws that make sure that the intelligence does not participate in a self -controlling process!

Source: Livescience