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.

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

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 ...

Developers are discovering that Model Context Protocol shines at providing AI coding agents with highly relevant software engineering context, on demand, at run time.