Qwen3.8-27B-pi: Effort-Ordered Reasoning for Agentic Coding
bytkim
• • 15NEW Articles from Team or Enterprise organizations will get promoted to the main section.
Write an Eval That Can Say No
ericmey
• Ten thousand synthetic policyholders: a practical guide for actuaries, economists and social scientists
alidenewade
• Training a Looped Transformer: When to Repeat, Review, and Stop
TiGa-RCE
• Introducing AURORA: A Multilingual Leaderboard for Frontier Models on Non-English Agentic Tasks
Lilt-org
• Gemini 4.0 Is Coming: What Google Confirmed, What Leaked, and How to Get Ready
liliruli
• • 1Diagnosing a slow Hugging Face Trainer run: data loading or compute?
abhinavsriva
• • 5Hunmin-CUA: Post-Training a 397B MoE for Computer Use
comoZ
• • 1autotrust/JEV-27B-VL: a decision model that learned to see without a single image of training
autotrust
• • 165Bekko System One: building ultra-small decision models that run in a browser
hotchpotch
• • 2S1MB: comparing System One Decision Models across 100+ benchmarks
hotchpotch
• • 2What Is Decisions API? OpenAI's Fast Decision Layer Explained
sora-2
• • 4Introducing ZooWork Instinct Tuned 4B — an open decision model
srpone
• Using Krea with reference images
OzzyGT
• • 1Four independent n8n templates for source-linked social research
karmen-beatapi
• Jev AI Workflows and Use Cases: A Practical Guide to Typed Decisions
sora-2
• The $100 Frontier Compute Problem
javadtaghia
• Anatomy of a bug-fixing agent
huggingface
• • 7Open Superconductor Challenge: Help Discover the Next 2D Superconductor — From Your Laptop
FINAL-Bench
• • 12BeatDesign: A Local Canvas and Timeline Your MCP Agent Can Work In
karmen-beatapi
•