On Feb. 10 and 11, the first Artificial Intelligence (AI) Action Summit will take place in Paris in France. As its widespread adoption throughout the world, especially in the case of the so-called generative intelligence, to pave the way for a society in which AI and those controlling it would have inordinate power and a new “social contract” could be imposed by a handful of billionaires, this summit is meant to initiate cooperation between countries and the Asian or U.S. major digital powers to supervise its development.

Health, environment, communication, industry, etc., there is no sector that can elude AI, including that of information and journalism. Regarding this, I “interviewed” an AI. I first asked it how AI could encourage the spread of fake news. Here is its response.

“Artificial intelligence (AI) will considerably facilitate the spread of false news in a number of ways:

. “Generating quickly and on a massive scale misleading contents: Generative AI makes it possible to produce quickly and on a large scale falsified text, images and videos. This capacity to automatically create considerably increases the volume of false news circulating.       

. “Improving realism: Contents generated by AI, and especially deepfakes, are becoming more and more realistic and difficult to distinguish from authentic contents. This increased sophistication makes false-news detection more complex for the public.

. “Personalization and targeting: AI makes it possible to develop campaigns of disinformation that are hyper targeted, adapting misleading messages to specific groups of users. This personalization increases the efficiency and impact of false information.            

. “Amplification through social networks: The bots fed by AI can automatize the spread of false information on social platforms, increasing their reach and virality. 

. “Increased credibility: A study has shown that false information generated by AI are perceived as more credible than those produced by humans, making them potentially more dangerous. 

. “The increasing accessibility of AI technologies makes it possible for a larger number of malicious actors to create and spread false informations.

.“Generative AI excels in the field of falsehood and disinformation invading, through a great deal of hyper trickery, the social networks but also film productions, audiovisual media or even the written press.” 

We are now warned. As the United States is now led by men for whom feeding the public lies through their social media does not pose any moral problem and whose billions of dollars will give even more power to AI. 

I also asked the AI how would AI modify the practice of journalism. My artificial interlocutor first reeled off a long list of advantages—documentation, verification of the information, help with writing—but however insisted, during a whole chapter on the ethical challenges and considerations, on the need for the “preservation of the journalistic integrity.

“It is crucial,” this AI said, “to maintain human supervision and editorial judgment to guarantee the accuracy and ethics of the contents generated or assisted by AI.”

However, this AI stressed, “the use of AI to collect and analyze data raises questions regarding individuals’ privacy protection.”  

Finally, the AI pointed out, “the media must be transparent regarding their use of AI in the production of contents in order to maintain the public trust.”

Everything that is in quotation marks in this text came from a machine. I would not have said it better. Normal since this machine has done nothing but compiling texts of human origin.

But what would happen if the machines would manage to emancipate themselves from the human bond or what will feed them tomorrow would be billions of informations and data that are false or invented for malicious purposes?

I asked my AI and it told me that the false informations would be even more difficult to pinpoint, the cyberattacks for blackmail or aggression purposes would multiply, etc. But, it added, AI could be developed to help humans counterattack. An AI against AI? Too bad that it’s too late to throw all this in the garbage can.