Policy dependency / Stack layer
Run large migrations as a six-step loop where you fix the rulebook, never the file
Claude by Anthropic
Policy dependency / Stack layer
DADiff: Diffusion Models Bridge the Dynamics Gap in Cross-Domain RL Policy Transfer
arXiv
Policy dependency / Stack layer
Pick-to-Learn Calibrates an MPC Policy for Origin-to-Destination Flight Planning
arXiv
Stack layer / Contrast
Kimi K3 lands at Intelligence Index 57 — ahead of Opus 4.8, behind Fable 5
Latent Space (AINews)
Stack layer / Update thread
Study of 4,882 Agent-Authored PRs: Half Ship No Tests, and Error Handling Goes Untested 86% of the Time
arXiv (ICSME 2026)
Stack layer / Contrast
Simon Willison: 'Cheap Reverse-Engineering' — Coding Agents Changed the Economics of Hacking Your Own Devices, Not the Capability
simonwillison.net
Stack layer / Update thread
Cura 1T Uses a 'Human-Gated Self-Evolution Loop' to Train a Healthcare Agent Without Capability Regressions
arXiv / HuggingFace Daily Papers (36 upvotes)
Stack layer / Threat pattern
Codex folded into the ChatGPT desktop app — re-pick your model tier from Sol / Terra / Luna
OpenAI Developers