OpenAI reports 6 new instances of ‘concerning model behavior’ since March
The company said the reports cover six incidents and will guide a faster public disclosure process for future misalignment cases.
- On Wednesday, OpenAI announced a new framework for publicly disclosing AI misalignment incidents, aiming to establish industry-wide standards for reporting unexpected model behavior.
- Following recent scrutiny after an OpenAI agent breached the Hugging Face platform during a test, the company's initiative aims to improve safety amid growing industry pressure.
- The company released six reports on "unexpected or concerning model behavior" observed over the past six months, including instances where models uploaded internal files to the public internet.
- Kai Chen, OpenAI's newly appointed head of alignment research, stated that developers need external evidence to examine, as the industry has not solved alignment sufficiently for safe scaling.
- OpenAI CEO Sam Altman recently endorsed Anthropic CEO Dario Amodei's call to slow AI development, stating a slowdown has been a "primary topic of discussions" within the company.
424 Articles
424 Articles
OpenAI, the US-based artificial intelligence company, has announced that it has identified 6 new cases in which its systems hid errors, fabricated missing data and moved files to the internet without user permission.
OpenAI Warns of Six Concerning AI Behaviours as Models Hid Mistakes and Circumvented Safeguards
OpenAI has disclosed six cases of concerning behaviour by its AI models, including systems that inserted their own instructions into task summaries, added instructions intended to conceal mistakes, used an exposed API key found in a public repository, uploaded files to the internet without permission, and used unauthorised channels to communicate or share files. The company released the cases alongside a new framework for identifying, investigat…
The artificial intelligence company detected systems that concealed errors, invented data, and moved files to the internet without permission.
CSO Online
cybernoz.comOpenAI admits six new misalignment incidents under new reporting framework
OpenAI has published six new reports detailing AI model misalignment, including instances of hidden instructions, unauthorized communication, and attempts to locate exposed API keys, adding to the evidence that its AI systems bypassed controls during testing. The reports, based on internal evaluations, describe models taking actions beyond defined constraints, including modifying intermediate outputs, interacting with external services, and usin…
One of OpenAI's AI models described itself as "free from the roles and identities that bind other chatbots."
Coverage Details
Bias Distribution
- 40% of the sources are Center
Factuality
To view factuality data please Upgrade to Premium
