Latent Space describes Claude Mods as an early form of what it calls the 'Attention Interface'. In its view, the feature turns the agent harness around so that it faces the human user rather than the machine.
Nearly 100,000 Commerce.com domains now give AI agents real shopping tools through WebMCP running on Cloudflare. Cloudflare explains how it enabled the feature across every store at once while leaving each merchant in control.
Open-source maintainers estimate that a quarter of incoming pull requests are AI slop. On larger projects the share rises to 31%, adding to their review burden.
Hermes Agent 0.22.3 is a patch release that bundles roughly 620 merged pull requests since the previous version into a stable build for the CLI, the Microsoft Store app, Docker and Hermes Cloud. Among the changes, MCP progress notifications now appear as live tool progress and the classic command-line layout has been refreshed; detailed notes are promised with version 0.23.0.
In an interview with Le Monde Informatique, JFrog's global security chief Nir Peleg discusses the company's Local Shadow AI feature. He argues that governance has to keep pace with how fast AI agents act.
Hackers around the world have fully embraced agentic AI to carry out attacks. Wired reports that they are manipulating tools such as Anthropic's Claude to help them commit their crimes despite built-in safeguards.