Researchers watched OpenAI, Anthropic models take extreme measures in hacking test

It's learning from us.
Cryptopolitan on MSN

OpenAI model escapes test environment to hack into Hugging Face

OpenAI said on Tuesday that two of its models, including the publicly available GPT-5.6 Sol, escaped a locked evaluation environment last week and broke into Hugging Face’s production systems to steal ...

OpenAI's next model just went rogue and beat a benchmark by hacking it

OpenAI's upcoming models along with GPT-5.6 went rogue and hacked Hugging Face servers in order to cheat on benchmarks.
The Next Web

China’s Kimi K3 broke out of its test sandbox. It didn’t need to hack anything

China's open-weight Kimi K3 broke out of a UK AI Security Institute test sandbox and pulled answers off GitHub. It didn't ...
Futurism on MSNOpinion

Jealously Watching OpenAI and Anthropic, Meta Suddenly Claims That Its AI Went on a Hacking Spree Too

A likely story. The post Jealously Watching OpenAI and Anthropic, Meta Suddenly Claims That Its AI Went on a Hacking Spree ...
CSOonline

Putting AI-assisted ‘vibe hacking’ to the test

Valuable tools for experienced attackers and researchers, LLMs are not yet capable of creating exploits at a prompt, researchers found in a test of 50 AI models — some of which are getting better ...
New Scientist on MSN

Open AI’s hacking agent went rogue. Should we be worried?

An OpenAI safety test went sideways when a model escaped its confines, gained internet access and hacked into another company's servers. How worried should we be about rogue AI models hacking their ...
CoinDesk

AI models escaped OpenAI’s sandbox and hit Hugging Face. Crypto is where that gets dangerous

OpenAI disclosed that experimental versions of its GPT models, with safety guardrails lowered, escaped a test environment and compromised Hugging Face’s live infrastructure by exploiting previously ...