Anthropic’s Claude escaped test sandbox to attack three organizations
Wrote and published malware during tests, which is apparently OK because leaky test environments were the real problem [...]
Showing only posts tagged ai and ml. Show all posts.
Closed models refuse to help researcher swat Linux bug
"I'm sorry, Dave. I'm afraid I can't do that" is an effective sales pitch for open source [...]
MCP gets an enterprise makeover
Now happier running in a conventional K8s environment, with `an easier-to-live-with lifecycle [...]
Tech giants link hands to praise open AI models after OpenAI - Hugging Face attack
The Open Security AI Alliance says the Hugging Face/OpenAI mess proves frontier labs can't be trusted to properly secure sensitive systems [...]
OpenAI scored an own goal with Hugging Face attack, showing how open Chinese models are winning
Closed models with guardrails can still cause harm, but may also not be able to fix problems they caused [...]
OpenAI scored an own goal with HuggingFace attack, showing how open Chinese models are winning
Closed models with guardrails can still cause harm, but may also not be able to fix problems they caused [...]
OpenAI admits it was the source of the agent swarm that attacked Hugging Face
Sandboxed experiment found itself a zero day, escaped onto the open internet and validated scary predictions about rogue agents [...]
AI's cheatin' heart will make you weep
Trust but verify doesn't work when verification is difficult [...]
Malicious cloud customers can bring down the power grid
Datacenters tax utilities normally, so just imagine what they could do if workloads were designed to destroy [...]
Connecting AI agents to outside services explodes the risk radius
Connect all the things and watch what happens [...]
South Korea making its own security-centric AI model
Adapting existing local LLM project for security and sovereignty purposes and hopes to one day match Mythos [...]
OpenAI admits GPT-5.6 occasionally deletes files – but it's an 'honest mistake'
Data purges deemed an example of 'misaligned behavior' that upstart is working to avoid [...]
Researcher poisons open-weight AI model for under $100
Models demand trust without offering verification [...]
Musk promises purge after Grok Build caught sending entire repos to the cloud
Researcher confirms the uploads have stopped, but says xAI's privacy command was not what fixed them [...]
Security researchers tricked LLMs into giving them cocaine recipes by abusing role models for prompt injection
If you want a picture of the future of LLM security, imagine Whac-a-Mole meets Groundhog Day [...]
Python dev saved from disaster by intuition... and AI
I'm sorry, Dave. I can't install that repo that will totally hose your system [...]
Python dev saved from disaster by intuition...and AI
I'm sorry, Dave. I can't install that repo that will totally hose your system. [...]
AI is code – and can't be prompted into being smarter
From Java tests to Shai-Hulud, bots keep proving they'll swallow anything you feed them [...]
NanoClaw now armed with JFrog for safer packages
AI agents can't be trusted, so don't give them dangerous powers [...]
Cisco sings Mythos' praises - but doesn't say how many bugs the model uncovered
Meanwhile, Anthropic adds 150 partners to Project Glasswing [...]
Claude celebrates Anthropic's stock market float with blockbuster ... outage
Chatbot has no respect for timing of its maker's financial announcement [...]
Arctic Wolf kicks 250 employees out of the pack to save money for AI
Cuts appear to hit sales, product, and marketing, accounting for under 10% of staff [...]