Shared entity / Policy dependency
Bedrock AgentCore Gateway publishes a four-scope maturity model and real per-operation pricing for agent tool access
AWS Machine Learning Blog
Shared entity / Stack layer
Latent Space: The Agent Harness Is Being Absorbed Into the Weights, and What's Left Will Be a Harness for Human Attention
Latent Space
Shared entity / Stack layer
Show HN: OzBrain Argues Notes Apps Were Built for Humans and Agents Need Their Own Store, Taking 84 Points
Show HN
Shared entity / Stack layer
Show HN: Proliferate (YC S25) Open-Sources a Self-Hostable IDE That Runs Claude Code, Codex, OpenCode, Cursor and Grok in One Place
Show HN
Shared entity / Stack layer
Cumora puts AI agents on the same team roster as humans, 2,891 stars in five days, with a bring-your-own-Claude-Code brain mode
GitHub
Stack layer / Threat pattern
Hydra's instantiate() gets a CVE for code execution from untrusted config
GitHub Security Advisories
Policy dependency / Stack layer
Zvi Mowshowitz: text watermarking is free because LLM outputs were already random, and Google proved it at n=20 million
Don't Worry About the Vase (Zvi Mowshowitz)
Stack layer / Contrast
Anthropic shipped its internal CI/CD on-call agent as a public setup kit, with skills in git and a lessons.md learning loop
Claude by Anthropic