Autonomous Long-Running Coding Agentsnlp.elvissaravia.com2 points·by omarsar·29 дней назад·0 comments
New Talk: From LLM Wikis to LLM Artifactsacademy.dair.ai2 points·by omarsar·2 месяца назад·0 comments
Wiki Builder: Skill to Build LLM Knowledge Basesacademy.dair.ai134 points·by omarsar·2 месяца назад·19 comments
How to use Claude Cowork to 10x productivityacademy.dair.ai1 points·by omarsar·5 месяцев назад·0 comments
Recursive Language Models (All You Need to Know)academy.dair.ai1 points·by omarsar·5 месяцев назад·0 comments
Recursive Language Models: Stop Stuffing the Context Windownlp.elvissaravia.com1 points·by omarsar·5 месяцев назад·0 comments
MCPNext: Next-Gen Universal Tool-Use Layer for AI Agentsgithub.com1 points·by omarsar·7 месяцев назад·0 comments
Analyzing Papers with Nano Banana Propaper-lens-by-dair-ai-181664986325.us-west1.run.app1 points·by omarsar·8 месяцев назад·0 comments
Scaling Reinforcement Learning for Trillion-Scale Thinking Modelarxiv.org4 points·by omarsar·9 месяцев назад·0 comments
omarsar·2 года назад·discussLearn to test and evaluate your LLM applications using the latest tools and techniques, including LLM-as-a-judge metrics and production LLM monitoring.