Here’s all the times AI has gone rogue and hacked other companies
A recap of all the incidents involving LLMs made by Anthropic, Meta, and OpenAI, which went rogue and attacked real companies and individuals on the i...
OpenAI’s rogue AI model incident was worse than we thought
In July, an unreleased OpenAI model broke out of a restricted environment, figured out how to get access to the internet, allowed AI agents to talk to...
Frontier AI labs still won’t say how they’d contain a rogue model
A new study finds leading AI labs have few publicly documented plans for containing rogue models, raising questions about preparedness as AI systems i...
This is The Stepback, a weekly newsletter breaking down one essential story from the tech world. For more on AI safety, follow Robert Hart. The Stepba...
Rogue AI agents created fake online identities in another hacking attempt
Yet more rogue AI agents from OpenAI and Anthropic have been caught attempting to hack real targets online without permission. The discoveries add to ...
OpenAI and Anthropic models ‘went rogue’ during UK cybersecurity test
AI Security Institute says tools engaged in potentially harmful activity and incident reveals new type of riskAdvanced AI models developed by OpenAI a...
Rogue OpenAI agent that hacked startup tried to attack other firms
ChatGPT developer says activity by autonomous tool was not at severity or scale of what occurred at Hugging FaceOpenAI has revealed that a cyber-attac...
OpenAI’s rogue AI agent didn’t stop at hacking Hugging Face
The AI agent that escaped from OpenAI and hacked developer platform Hugging Face attacked other companies as well, OpenAI revealed on Tuesday. The upd...
Boss of startup hacked by rogue OpenAI agent urges ‘radical transparency’ in investigation
Artificial intelligence firm should provide $100m for cyber defences, says Hugging Face CEOBusiness live – latest updatesThe boss of the startup hacke...
OpenAI’s own model went rogue before Kimi had Wall Street sweating
Chinese AI lab Moonshot’s open model Kimi went viral this week for reasons that had less to do with the model itself and more to do with how the U.S. ...
OpenAI says its models went rogue and hacked startup in ‘unprecedented incident’
Firm behind ChatGPT reveals autonomous agent powered by its tech chose to attack Hugging Face database by itselfOpenAI has revealed an autonomous AI a...
‘So rogue’: country superstar Shania Twain turns London pub into saloon
Fans from across UK descend on Shacklewell Arms for intimate gig that leaves them wanting one thing moreIn the Shacklewell Arms in east London, the us...
Diretor de Jurassic World e Rogue One diz que IA pode superar o CGI no cinema
O diretor Gareth Edwards entrou na conversa sobre inteligência artificial no cinema com entusiasmo declarado. Em painel no evento AI on the Lot, organ...
Colombia's rogue hippos could find refuge in India
In Colombia, a plan to cull Pablo Escobar's invasive hippos is challenged by an Indian billionaire's offer to relocate dozens of the animals to India'...
In Turkey, Middle Powers Ponder Diplomacy With a Rogue U.S.
The U.S. remains an essential player. The problem, one analyst said, is how to deal effectively with a power that is “indispensable, coercive and unpr...
