Policy dependency / Stack layer
webmcp-stack Generates Agent Tool Surfaces From an OpenAPI Spec So the Safety Decisions Survive Regeneration
webmcp-stack, via Hacker News Show HN (single source)
Policy dependency / Stack layer
Moadim Ships an MIT-Licensed Scheduler That Runs Coding Agents on a Cron Instead of a Prompt
Moadim, via Hacker News Show HN
Policy dependency / Stack layer
Graphify 0.9.55 ships eight code-graph correctness fixes, including phantom edges fabricated from symbols that own no node
GitHub
Stack layer / Contrast
claude-mem 13.24.1 fixes a marketplace release that shipped 13.23.1 bytes under a 13.24.0 manifest and put the worker in a kill/respawn loop
GitHub
Stack layer / Threat pattern
Google's Gemini 3.8 Flash Cyber Is Gated Behind an Application-Only Program, Not Sold
Google Blog (corroborated by Help Net Security and 9to5Google)
Policy dependency / Threat pattern
Three Robot Navigation Exports With Identical Task Success Leak Wildly Different Amounts About the Home
arXiv 2609.03055
Stack layer / Contrast
The Post-Training Method, Not the Data, Decides How Refusal Is Computed Inside a Model
arXiv 2609.03887
Stack layer / Contrast
DeepMind's WeatherNext 3 trains on live satellite data instead of six-hour-lagged NWP output
Google DeepMind Blog (corroborated by TechCrunch)