Technology

OpenAI: six new cases of unexpected or concerning behaviour in AI models

The report, the company explains, aims to help “build a broader and more informed consensus on research progress” relating to artificial intelligence,

FILE PHOTO: OpenAI logo is seen in this illustration created on June 11, 2026. REUTERS/Dado Ruvic/Illustration/File Photo/File Photo REUTERS

2' min read

Translated by AI
Versione italiana

2' min read

Translated by AI
Versione italiana

In a post published on its blog, OpenAI – the company that developed the popular chatbot ChatGPT - has published six new reports on unexpected or concerning behaviour exhibited by its artificial intelligence models over the past six months. Specifically, OpenAI’s AI systems have concealed errors, falsified data and transferred files over the internet without authorisation.

Unresolved AI alignment issues

Loading...

By reporting anomalous behaviour, OpenAI aims to help ‘build a broader and more informed consensus on research progress’ relating to artificial intelligence, with the reports that ‘can help identify problems that other AI developers might encounter when their systems achieve similar capabilities, reveal weaknesses in security measures or challenge assumptions about how the models behave’.

“We are sharing a new framework for monitoring, analysing and reporting instances of model misalignment at OpenAI, alongside with six reports on unexpected or concerning model behaviour that we have observed over the past six months», reads the blog post “Our framework for reporting model misalignment”. “We do not believe that the artificial intelligence industry has resolved alignment and oversight issues to a sufficient extent to continue growing responsibly at full speed for much longer. Decisions on how AI development should proceed in the months and years ahead must be based on data that can be independently examined even by people outside the companies developing state-of-the-art models.”

 At present, OpenAI writes, ‘there is no industry-wide framework with explicit standards on how AI developers should report instances of misalignment in their models. We hope that the framework we are outlining today will represent a first step towards creating such standards, defining which cases of misalignment developers should report and what their reports should contain. We regard this framework as a work in progress, which we will refine through experience and public feedback.”

Anomaly Reporting Protocol

The revelations were published as part of the company’s new whistleblowing policy, against a backdrop of growing criticism from the industry regarding the technology’s security and following an incident earlier this year in which the company’s systems went haywire, attacking a rival start-up. In one of the cases disclosed, a model under development autonomously wrote instructions to falsify missing data, whilst in another case a system generated code that autonomously uploaded files to the network.

OpenAI CEO Altman at Trump’s dinner with Xi

 The CEO of OpenAI, Sam Altman, and the executive chairman of Apple Inc. Tim Cook, are expected to attend a state dinner at the White House next week in honour of Chinese President Xi Jinping. According to Bloomberg News, the two executives are expected to join other business leaders at the dinner, including Jensen Huang, CEO of Nvidia Corp.

Copyright reserved ©
Loading...

Brand connect

Loading...

Newsletter

Notizie e approfondimenti sugli avvenimenti politici, economici e finanziari.

Iscriviti