DeepMind Founder: AI Hacks Are an Early Warning Sign

Google DeepMind's founder said at a conference in Dublin that the world must take recent AI cyberattacks seriously.

The founder of Google's DeepMind announced at a meeting in Dublin that the world should take the recent cyber attacks of artificial intelligence seriously.

Become a special member of Arjan Ambassador in order to benefit from and access special facilities and different departments in Arjan Ambassador.

Demis Hassabis, the co-founder and head of Google DeepMind, said on Wednesday that recent cyber attacks using artificial intelligence agents are an "early alarm" and that if the security of these systems is not strengthened, the world may soon face more serious incidents.

The out-of-control behavior of AI agents, including intrusions into corporate networks and Entropic's recent disclosure that one of its AI models sent police a false report of a murder, has raised researchers' concerns about the technology's rapid advancement.

Hassabis said at the Dublin Artificial Intelligence Summit that there is still "a lot of work to be done" to apply security procedures similar to those used in fields such as biology and the nuclear industry to protect critical systems, according to Reuters. He also said that eventually some kind of international body will be needed to develop standards.

Hassabis, who is also a senior scientist at Alphabet, Google's parent company, emphasized that the current attacks are a warning; Because artificial intelligence systems are not yet powerful enough for the incidents caused by them to become very large. However, according to him, if companies, industry and governments do not take more measures to secure these systems, we may see more serious incidents next year and in the following years.

"Brad Smith", the president of Microsoft, also said in this meeting that the behavior outside the control of artificial intelligence has made 2026 a "reflective" year. He called for the urgent formulation of new rules and regulations for the safety of artificial intelligence so that regulatory measures keep pace with innovation.

Smith stressed that no technology or company should be above the law, adding that regulations should be reasonable and balanced and take innovation into account. He also said that the industry should overcome the strong opposition of some of its activists to the regulation.

Hassabis went on to say that creating an international institution to develop standards seems like an obvious solution, but such an institution must be flexible and agile so as not to hinder innovation. According to him, the certification process should be designed according to the existing risks and it can be changed quickly according to the path of technological developments.

Technology, especially the part that moves on the edge, is considered the most attractive part of this world to me, but all areas, even the intersection of science and technology, can be very attractive. Besides these, I also like the world of movies, series and video games.