ai
Tool Poisoning and MCP Security: When Your Agent's Toolbox Is the Weapon
MCP tool descriptions are instructions, not metadata. Here's how attackers exploit that — and what the benchmark data actually shows about model safety alignment.
Articles about artificial intelligence, machine learning, and AI systems
ai
MCP tool descriptions are instructions, not metadata. Here's how attackers exploit that — and what the benchmark data actually shows about model safety alignment.
framework
A new ETH Zurich study finds that LLM-generated context files reduce task success rates and raise inference costs by 20%. Here's what the data actually shows.
culture
The clinical term 'AI psychosis' is now documented in peer-reviewed literature. Here's what's driving hospitalizations, cognitive decline, and a massive uncontrolled experiment.
ai
SOTA vision-language models fail at spatial tasks trivial to humans. Why perception gaps matter for reliable AI systems.