Researchers broke every AI defense they tested. Here are 7 questions to ask vendors.

Researchers from OpenAI, Anthropic, and Google DeepMind found that adaptive attacks bypassed 12 AI defenses that claimed near ...
InfoQ

Ramp Builds Internal Coding Agent That Powers 30% of Engineering Pull Requests

Ramp has shared the architecture of Inspect. This internal coding agent has quickly reached about 30% adoption for merged ...

Anthropic has to keep revising its technical interview test as Claude improves

The issue of AI cheating is already wreaking havoc at schools and universities around the world, so it's ironic that AI labs ...

Anthropic's test to hire engineers had this Claude 'problem', here's how the company solved it

AI startup Anthropic faced a unique hiring challenge as its own Claude models began outperforming human candidates on ...
Dark Reading

'Contagious Interview' Attack Now Delivers Backdoor Via VS Code

Once trust is granted to the repository's author, a malicious app executes arbitrary commands on the victim's system with no ...