Shared entity / Stack layer
Sebastian Raschka says delete or regenerate your AGENTS.md and SKILL.md files, because the hand-holding now constrains newer models
Ahead of AI (Sebastian Raschka)
Policy dependency / Stack layer
CROSS-CATEGORY: Three Independent Agent-Action Gates Shipped in 48 Hours, All Judging the Command Against Stated Intent
Product Hunt, github.com/AGGIB/Stroq and rewarelabs.com (three independent sources; the 72% figure is Reware's own)
Policy dependency / Stack layer
Retrieval that crosses into your dependencies' source, not just your repo, adds up to 6.3% pass@1 and survives version changes
arXiv 2609.09987
Policy dependency / Contrast
A Fine-Tuned 4B Qwen in 2.6 GB Beats GPT-5.6 on a Transit-Kiosk Agent Benchmark, and PEFT Gains Vanish by 27B
arXiv 2609.10016
Stack layer / Update thread
YuE2-3B ships open weights claiming a SongBench win over Suno v5, but the weights are non-commercial
M-A-P / HKUST
Stack layer / Follow-up thread
Φ-Bench tests whether LLMs can engineer their own serving and training stack, from kernels to end-to-end optimization
arXiv
Policy dependency / Contrast
Thousand Launches Git-Backed Markdown Docs Where Teammates, Outsiders and Agents Each See Only Their Folders
Thousand (via the Product Hunt leaderboard for 2026-09-10; single source)
Stack layer / Follow-up thread
Models Spot Only 9.6% of Implementation Gaps in Research Specs but Fix 80.6% Once You Point Them Out
arXiv 2609.10539