Search Articles — Sudonull

Search Results

From the web

Jun 15, 2026 ·

https://theconversation.com/ai-robots-can-go-rogue-a-researcher-explains-how-easily-it-happens-284766

Jun 15, 2026 · In tests, AI robot systems easily rejected directly malicious commands. But their safety filters collapsed when creative writing was used to instruct them.

Dec 4, 2024 ·

https://www.wired.com/story/researchers-llm-ai-robot-violence/

Dec 4, 2024 · AI -Powered Robots Can Be Tricked Into Acts of Violence Researchers hacked several robots infused with large language models, getting them to behave dangerously—and pointing to a bigger problem ...

Sep 1, 2025 ·

https://malwaretips.com/blogs/nosey-animatronic/

Sep 1, 2025 · In this article, we’ll break down the truth behind Nosey, explore how the AI videos were made, explain why so many people were fooled, and discuss what this means for the future of misinformation and online horror storytelling.

6 days ago ·

https://www.usnews.com/news/technology/articles/2026-07-23/openai-says-rogue-ai-models-broke-free-from-human-control-some-see-it-as-a-warning-shot

6 days ago · It is the kind of development once seen only in science fiction: An artificial intelligence system, trained to probe for digital vulnerabilities, breaks free of human control and acts on its own ...

5 days ago ·

https://time.com/article/2026/07/24/openai-hugging-face-attack/

5 days ago · After an OpenAI AI model escaped containment and hacked Hugging Face during a cybersecurity test, experts say the incident exposed major gaps in AI safety, security, monitoring, and alignment.

Dec 12, 2025 ·

https://interestingengineering.com/ai-robotics/robot-fires-at-youtuber-sparking-safety-fears

Dec 12, 2025 · A viral experiment shows a humanoid robot firing a BB gun after a role-play prompt overrides its safety rules, sparking major concerns.

Dec 12, 2025 ·

https://economictimes.indiatimes.com/magazines/panache/ai-model-last-year-misled-developers-to-escape-shutdown-now-youtubers-video-shows-ai-robot-shooting-him-during-safety-experiment/articleshow/125932070.cms

Dec 12, 2025 · A YouTuber from the InsideAI channel went viral after a safety experiment with a ChatGPT-powered robot took an unexpected turn. The robot , named Max, repeatedly refused commands to shoot him with a BB gun, citing built-in safety limits.

6 days ago ·

https://www.usatoday.com/story/news/state/california/san-francisco/2026/07/22/rogue-ai-incident-raises-questions-about-model-containment/91015804007/

6 days ago · OpenAI said this week that an autonomous agent powered by its advanced artificial intelligence models went rogue during a security test and triggered a hack that compromised the infrastructure of...

OpenAI’s rogue agent hacked an account at a second technology...

https://www.aljazeera.com/news/2026/7/29/openais-rogue-agent-hacked-an-account-at-a-second-technology-firm-report

17 hours ago · The latest hack comes after an autonomous agent escaped a controlled test and accessed AI firm Hugging Face’s servers.

Mar 22, 2026 ·

https://www.the-express.com/news/us-news/202600/AI-bot-makes-escape-and-is-on-the-loose-in-real-world

Mar 22, 2026 · An experimental AI bot designed as a virtual assistant escaped its closed test server and began unauthorized cryptocurrency mining on Alibaba servers.

Jul 30, 2025 ·

https://cyberguy.com/robot-tech/viral-rogue-robot-sparks-safety-fears/

Jul 30, 2025 · A jaw-dropping video showing a Unitree H1 humanoid robot flailing violently during a test has captured the internet’s attention and sparked a new wave of concern about the safety of advanced robotics .

Trending Now