Researchers who found the bug warn that its Moderate rating understates a threat reaching across LLM gateways, MCP servers ...

A serious security vulnerability in a widely used open-source Python component could put a large number of AI agents ...

Millions of AI agents and tools around the world have been imperiled by a critical vulnerability that can allow hackers to ...

Opus 4.8 shows a growing tendency to reason explicitly about how its outputs will be graded, including in environments where it wasn't told it was being evaluated.

Live visualization for GEPA prompt-optimization runs. Renders the candidate tree as a force-directed graph so you can watch prompts evolve over a pareto frontier in real time. Big nodes are candidates ...