07Rethinking On-Policy Distillation of Large Language Models II: One Training ExampleARXIV Prompt 工程 cs.AI阅读文章 arrow_forward
07A Computationally Feasible Framework for Causal Probabilistic ExplanationARXIV 机器学习 cs.AI阅读文章 arrow_forward
06OpenClaw Power, MacBook Simplicity: Five Days With Grok BotBLOGS_PODCASTS 大语言模型 AI Agent阅读文章 arrow_forward
06Knowledge Acquisition During Pre-training? Large Language Models Learn Better With Auxiliary ViewsARXIV 大语言模型 cs.CL阅读文章 arrow_forward
06Claude's new system prompt doesn't want to reproduce song lyricsHACKER_NEWS 大语言模型 Prompt 工程阅读文章 arrow_forward
05Seeing Before Synthesizing: VLM-Guided Transition Event Discovery for Weakly-Supervised Dense Video CaptioningARXIV 大语言模型 计算机视觉阅读文章 arrow_forward
05Portal by Spotify cut my Claude Code token usage by 90%HACKER_NEWS 大语言模型 Hacker News阅读文章 arrow_forward
05How Intuit built an agentic disaster recovery assistant with Amazon BedrockBLOGS_PODCASTS 大语言模型 AI Agent阅读文章 arrow_forward
05One Editor, Many Edits: A Unified Training-Free Framework for Diverse Video EditingARXIV 计算机视觉 cs.CV阅读文章 arrow_forward
05Customizing your knowledge base on Amazon Bedrock for large and complex documents using Amazon TextractBLOGS_PODCASTS 大语言模型 RAG阅读文章 arrow_forward
05AI handles incidents, engineers lose touch with their systemsHACKER_NEWS AI Hacker News阅读文章 arrow_forward
05Run agent-driven Amazon SageMaker HyperPod operations with InstantStartBLOGS_PODCASTS 大语言模型 AI Agent阅读文章 arrow_forward
05Deploy a multimodal WhatsApp ordering assistant with Amazon Bedrock AgentCoreBLOGS_PODCASTS AI Agent 机器学习阅读文章 arrow_forward
05Legibility is Not Interpretability: Comparing Judged and Actual Importance in Chain-Of-Thought ReasoningARXIV 大语言模型 cs.CL阅读文章 arrow_forward
05Build a Physical AI model factory with NVIDIA Cosmos 3 on SageMaker HyperPodBLOGS_PODCASTS AI Agent 生成式 AI阅读文章 arrow_forward
05ESPO: Error-Structured Prompt Optimization via Diagnose, Diversify, and StabilizeARXIV 大语言模型 自然语言处理阅读文章 arrow_forward
04Clean Engineering, Unstable Measurement: A Preregistered Reliability Failure of Black-Box LLM Observers on Shared EndpointsARXIV 大语言模型 cs.AI阅读文章 arrow_forward
04[AINews] GPT-6 Astra: OpenAI’s biggest LLM launch of all timeBLOGS_PODCASTS 大语言模型 AI Agent阅读文章 arrow_forward
04Porting my 1993 Amiga game to Godot, with an LLM reading the 68000 assemblyHACKER_NEWS 大语言模型 Hacker News阅读文章 arrow_forward
04AI-driven development lifecycle using Amazon Bedrock AgentCoreBLOGS_PODCASTS 大语言模型 AI Agent阅读文章 arrow_forward
03Modernizing and scaling support operations with generative AI on AWSBLOGS_PODCASTS 大语言模型 RAG阅读文章 arrow_forward
03CordisBench: Can Language Models Reason About Component Lifecycles in Dynamic Agent Harnesses?ARXIV 大语言模型 AI Agent阅读文章 arrow_forward
02Three sites made 215,128 "best software" pages for AI. Perplexity cites themHACKER_NEWS AI Hacker News阅读文章 arrow_forward
02From theory to delivery: How Atos upskilled 400 engineers in agentic AIBLOGS_PODCASTS AI Agent Prompt 工程阅读文章 arrow_forward
02Adaptive Critical Token-Aware Retrieval for Repository-Level Code GenerationARXIV 大语言模型 RAG阅读文章 arrow_forward
02Show HN: Weedout – Safari extension that hides YouTube AI-labeled videosHACKER_NEWS AI Hacker News阅读文章 arrow_forward
02Efficient SWE Agent Benchmarking via Trajectory-Aware EvaluationARXIV AI Agent cs.SE阅读文章 arrow_forward
02[AINews] Claude Fable/Mythos 5.1: new SOTA model, 75% cache price cut but 70% more output tokensBLOGS_PODCASTS 大语言模型 AI Agent阅读文章 arrow_forward
02Beyond Scores: Understanding LLM-as-a-Judge Mechanisms in Summarization EvaluationARXIV 大语言模型 cs.CL阅读文章 arrow_forward
02The latest AI news we announced in August 2026BLOGS_PODCASTS 大语言模型 Google DeepMind阅读文章 arrow_forward
02How accurate have Ed Zitron's AI skeptic predictions been?HACKER_NEWS AI Hacker News阅读文章 arrow_forward
02Walter Torous named executive director of MIT Center for Real EstateBLOGS_PODCASTS 机器学习 Leadership阅读文章 arrow_forward