Every processed story in chronological order, with the newest coverage first. Filter by tag, source, or score to drill in.
A government export-control directive — not a vendor decision — wiped out an active two-day agentic workflow, demonstrating that the off-switch for closed frontier AI can sit entirely outside both the vendor's and the developer's hands.
ClawCodex makes Claude Code's dynamic multi-agent workflow authoring available as open-source Python, removing the dependency on Claude Code itself for developers who want to build, save, and run model-authored pipelines.
The plugin consolidates what the source describes as a slow, manual, multi-source research process into a single structured workflow, replacing scattered inputs with a decision-ready dashboard and exportable deliverables.
The bug causes users running multi-step Claude Code sessions to be charged at the 1.25x cache-write rate for dozens of full-context rewrites of identical content, rapidly exhausting the 5-hour usage window in minutes rather than hours.
The release retires the monitors feature flag and raises the org limit to 20 while pushing multiple v4 data-pipeline reads to the events table, advancing Langfuse's v4 architecture migration for both cloud and self-hosted users.
Plumbref offloads the verification burden from the user to the agent itself, replacing the manual "are you sure?" follow-up loop with a structured, locally-run claim-checking step built into the MCP workflow.
The setup demonstrates a practical, host-native alternative to VM-based sandboxing for Claude Code, using standard Unix multi-user isolation to keep credentials and secrets out of the AI's reach without the complexity of virtualization.
The shutdown establishes a precedent in which the U.S. government can invoke export-control authority to immediately remove a frontier AI model from public access, raising the question of whether the most capable AI systems will remain available to general users or become restricted to a small number of approved entities.
LSEG's MCP integration is a concrete example of a major financial data provider piping institutional-grade, trust-assessed data directly into customer AI workflows via ChatGPT, rather than requiring customers to handle data ingestion and alignment themselves.
A new article in the agentic coding space documenting a real-world progression from a simple script to an MCP server.