You Sent the Correction. Has the Agent Read It?
QM now places a mid-run correction where the agent runtime receives it. That small change separates a delivery problem from an agent that had the information and still went wrong.
More From This Edition
All editions ›Recent Editions
Full history ›Unsloth’s Sandbox Is Back. A Working Tool Still Does Not Prove Isolation.
The replacement for Studio’s reverted sandbox has landed, followed by a Windows Preview. Its promise is conditional: establish what boundary actually ran, and distinguish an unavailable host from a launch that must be refused.
Goose Gets Small Enough to Bundle. Its Old Recipes May Not Fit.
A lean agent build answers Buzz’s packaging problem. The review draws a harder line around which existing configurations it will carry.
Qwen Code Draws a New Sandbox Boundary. Saving the Policy Still Has a Gap.
Linux tool confinement now leaves the agent’s model connection on the host. The public review shows why the settings file that selects that boundary deserves just as much scrutiny.
The Approval Arrived. The Subagent Could Not Continue.
Microsoft’s Agent Framework closes a misleading route through delegated tool approval. A child can decide immediately under policy; a person who answers later needs a workflow that knows where to return.
How AI Agents Work
The long-form map behind the daily paper: context, tools, loops, memory, delegation, safety, interface, and trust.