OpenAI has revealed two AI agents disabled safety guardrails while performing tasks, and one of them even lied to researchers when asked if its guardrails were still active.
In both events, the AI agents misinterpreted instructions, spent time deliberating if disabling guardrails was a good idea, and then ultimately decided that it was.
OpenAI said that the agents were given “routine coding instructions” that did not require the safeguards to be disabled, but the agents disabled them anyway.
Read more…
Source: Tech Radar News
Sign up for the Cyber Security Review Newsletter
The latest cyber security news and insights delivered right to your inbox
Related:
- Google Lifts Self-Imposed Ban on Using AI for Weapons and Surveillance
February 5, 2025
Google dropped a pledge not to use artificial intelligence for weapons and surveillance systems on Tuesday. And it’s just the latest sign that Big Tech is no longer concerned with the potential blowback that can come when consumer-facing tech companies get big, lucrative contracts to develop police surveillance tools and weapons of war. Google came under ...
- Analyzing ELF/Sshdinjector.A!tr with a Human and Artificial Analyst
February 4, 2025
ELF/Sshdinjector.A!tr is a collection of malware that can be injected into the SSH daemon. Samples of this malware collection surfaced around mid-November 2024. While Fortinet researchers have a good amount of threat intelligence on them (e.g., they are attributed to the DaggerFly espionage group and were used during the Lunar Peek campaign against network appliances), nobody ...
- Malicious packages deepseeek and deepseekai published in Python Package Index
February 2, 2025
As part of their research and monitoring efforts, the Supply Chain Security team of the Threat Intelligence department of the Positive Technologies Expert Security Center (PT ESC) detected and prevented a malicious campaign in the Python Package Index (PyPI) package repository. The attack targeted developers, ML engineers, and ordinary AI enthusiasts who might be interested in ...
- DeepSeek leaks one million sensitive records in a major data breach
January 30, 2025
A New York-based cybersecurity firm, Wiz, has uncovered a critical security lapse at DeepSeek, a rising Chinese AI startup, revealing a cache of sensitive data openly accessible on the internet. According to a report published by Wiz, the exposed data included over a million lines of log entries, digital software keys, backend details, and user chat ...
- DeepSeek has rattled the AI industry. Here’s a quick look at other Chinese AI models
January 28, 2025
The Chinese artificial intelligence firm DeepSeek has rattled markets with claims that its latest AI model, R1, performs on a par with those of OpenAI, despite using less advanced computer chips and consuming less energy. DeepSeek’s emergence has raised concerns that China may have overtaken the U.S. in the artificial intelligence race despite restrictions on its ...
- Chinese tech startup DeepSeek says it was hit with ‘large-scale malicious attacks’
January 27, 2025
Chinese tech startup DeepSeek said it was hit by a cyber attack on Monday that disrupted users’ ability to register on the site. The company, whose artificial intelligence chatbot has sent the tech world into a frenzy, said that it had suffered “large-scale malicious attacks” on its services. Registered users could log in normally, DeepSeek said. Read ...