Every processed story in chronological order, with the newest coverage first. Filter by tag, source, or score to drill in.
Enterprise teams that built agentic CI/CD workflows on Cursor's multi-model routing now face the prospect of that abstraction layer collapsing into a single-vendor dependency, with model behavior changes arriving silently inside Cursor's SDK rather than as detectable errors.
The benchmark shows that for autonomous coding agents, the choice between GLM 5.2 and MiniMax M3 reduces to a concrete cost-accuracy tradeoff: GLM's correctness edge is real but narrow and concentrated in greenfield packaging, while MiniMax delivers nearly the same results on modification tasks at roughly one-third the cost and half the latency.
A recurring failure across most audited MCP servers points to a systemic gap in current MCP server implementations.
Surface extends coding agents beyond the text channel by giving them the ability to autonomously build, serve, and react to structured HTML interfaces — removing the back-and-forth of chat for tasks that benefit from richer UI interaction.
The post reframes MCP defense away from input filtering toward hardening server-side handlers, arguing that a safe handler is a structural wall while input filtering is only a sieve — a distinction that changes where security effort should be concentrated.
BEAST introduces a repair-and-governance layer that intercepts malformed or non-compliant LLM outputs before they reach the filesystem, directly addressing the silent code corruption and token waste the source describes as current AI coding agent failure modes.
Shazeer's move from Gemini co-lead to OpenAI is a direct talent loss for Google's flagship AI model effort, arriving weeks after a major product showcase and amid OpenAI's IPO preparations.
The integration connects Adobe's marketing data directly into Amazon Quick via MCP, enabling campaign insights — including audience rankings and conflict recommendations — to be retrieved without leaving the Amazon Quick environment.
A hands-on test of 74 MCP servers across two major agentic coding clients in isolated microVM environments.
MCP server configs for widely used tools like Claude Desktop, Cursor, and VS Code have become an active supply chain attack surface — as demonstrated by the MCPoison and ContextCrush incidents — and MCPConfigCheck provides the first dedicated, zero-install scanner for these files.