Every processed story in chronological order, with the newest coverage first. Filter by tag, source, or score to drill in.
The structured shared history design directly resolves the tradeoff between inter-module context blindness and context rot, recovering cache prefix consistency while keeping per-module token consumption bounded in enterprise agentic systems.
The post identifies a gap in standard AI cost tooling: provider dashboards report spending after calls execute, but agents can accumulate runaway costs across many steps before any dashboard alert fires, making a pre-call interception layer the only point where spending can actually be stopped.
The addition of GitHub and Slack triggers alongside computer use support expands Cursor Automations beyond its previous trigger set, enabling agents to respond to a broader range of external events.
The paper provides a measurable, formal account of how evaluation bias spreads in multi-agent LLM pipelines and identifies a concrete structural intervention — expanding evaluator committee size — that reduces that spread by 72.4%.
Kimi K2.7 Code delivers substantial benchmark improvements over its predecessor while cutting reasoning token usage by 30%, making a capable open-weights coding model more efficient and freely accessible.
Claude Code's new HTML deployment capability extends Artifacts from a single-user output format to a shareable team communication tool for architecture, analysis, and prototyping work.
EMA replaces thousands of manual, per-user OAuth consent flows with centralized IdP-governed authorization, closing the audit, offboarding, and compliance gaps that standard MCP auth leaves open at enterprise scale.
Cursor's mobile app and cloud-agent migration capability let agents continue running after a developer closes their laptop, decoupling coding work from the local machine.
Iris replaces screenshot-based or assumption-based verification with runtime evidence from a live app, giving coding agents a concrete, structured verdict on whether their changes actually worked.
The release gives developers a publicly modifiable interface between trading commands and AI tooling, with live-order security caveats flagged as a factor that could affect the reliability of systems built on it.