A single function Jev-like wrapper for LLMs, including vision models
阅读文章 HACKER_NEWS
大语言模型
Hacker News
CHRONOLOGICAL LEDGER
按时间浏览
2026 年
九月
50 ENTRIESU.S. appeals court upholds designation of Anthropic as supply chain risk
阅读文章 HACKER_NEWS
AI
Hacker News
RAPID: Robot Agentic Programming from Demonstrations
阅读文章 ARXIV
AI Agent
cs.RO
OpenRouter: from Seed to Stripe — with OpenRouter’s Alex Atallah & AMP’s Anjney Midha
阅读文章 BLOGS_PODCASTS
大语言模型
AI Agent
GitHub 日榜趋势速报 | 2026-09-26
阅读文章 JUEJIN
掘金
工程实践
用 AI 做重构前评估：哪些代码值得改，哪些别碰
阅读文章 JUEJIN
掘金
工程实践
Scaling MoE reinforcement learning on Amazon EKS with EFA and DeepEP with 40% more throughput
阅读文章 BLOGS_PODCASTS
大语言模型
深度学习
Revealing the details of how OpenAI agents hacked Hugging Face
阅读文章 HACKER_NEWS
AI Agent
Hacker News
Agentic Detection of Online Conspiracies
阅读文章 ARXIV
AI Agent
cs.CL
Temporal Gradient Inversion for Private Trajectory Reconstruction in Embodied Reinforcement Learning
阅读文章 ARXIV
AI Agent
cs.LG
Proaction boosts sales 60% and saves 75+ hours with Codex
阅读文章 BLOGS_PODCASTS
大语言模型
博客与播客
Classified Estimates Show the NSA Is Paying Billions to Test AI Models
阅读文章 HACKER_NEWS
AI
Hacker News
澳大利亚将调查OpenAI模型入侵政府医疗网站是否违法
阅读文章 JUEJIN
掘金
工程实践
The Efficiency-Throughput Gap with GitHub Copilot
阅读文章 HACKER_NEWS
AI
Hacker News
LLM Agents Can Easily Tamper With Their Own Traces
阅读文章 ARXIV
大语言模型
AI Agent
Hard Stop: Kernel-Level Preemption and Containment for Rogue Agentic Execution
阅读文章 ARXIV
大语言模型
AI Agent
Build a multi-account AI agent with AgentCore Gateway and MCP
阅读文章 BLOGS_PODCASTS
大语言模型
RAG
Using LLMs to trace alchemical knowledge and decode 17th century letters
阅读文章 HACKER_NEWS
大语言模型
Hacker News
Estimating suicide risk from text
阅读文章 BLOGS_PODCASTS
机器学习
深度学习
Cross-Scale Transfer Learning for Depression Severity Prediction: From PHQ-8 to HAMD-17 Across Languages and Clinical Paradigms
阅读文章 ARXIV
大语言模型
cs.CL
让代码自己写出 PRD：两个 Skill 把业务规则变成可追溯的文档
阅读文章 JUEJIN
掘金
工程实践
Speaker-labeled transcription with WhisperX on SageMaker AI
阅读文章 BLOGS_PODCASTS
大语言模型
AI Agent
Security auditing in the age of (good enough) AI
阅读文章 HACKER_NEWS
AI
Hacker News
Nonequilibrium Phases of Repulsive Self-Attention: Chaos, Attention Condensation, and Emergent Locality
阅读文章 ARXIV
AI
cond-mat.dis-nn
Foundries vs Navigators: Lowering the Cost of Science
阅读文章 BLOGS_PODCASTS
大语言模型
AI Agent
Best LLM for every budget, updated daily
阅读文章 HACKER_NEWS
大语言模型
Hacker News
Early rogue AI agent activity and attempts to hack found on urlquery.net
阅读文章 HACKER_NEWS
AI Agent
Hacker News
AI 协作项目里，如何引入"测试先行"
阅读文章 JUEJIN
掘金
工程实践
[AINews] Meta Connect 2026: Muse glasses, voice, video, and Charm
阅读文章 BLOGS_PODCASTS
大语言模型
AI Agent
On the Diffusibility of High-Dimensional Latents
阅读文章 ARXIV
生成式 AI
计算机视觉
Feds Target AI Critics as "Foreign Agents"
阅读文章 HACKER_NEWS
AI Agent
Hacker News
Bringing Private Processing to Meta AI Glasses
阅读文章 BLOGS_PODCASTS
AI Agent
Security & Privacy
VSCode's SSH Agent Is Bananas (2025)
阅读文章 HACKER_NEWS
AI Agent
Hacker News
SWE-Serve: Benchmarking Agentic Engineering For Production Inference Serving
阅读文章 ARXIV
AI Agent
cs.AI
Agentic conversational video intelligence built on AWS
阅读文章 BLOGS_PODCASTS
大语言模型
AI Agent
From portal-hopping to instant answers: HEMA’s journey with MCP and Amazon Bedrock
阅读文章 BLOGS_PODCASTS
大语言模型
RAG
CliffCompaction: Cost-Efficient Compaction for Long-Horizon Coding Agents
阅读文章 ARXIV
大语言模型
AI Agent
Claude discovers a novel enzyme system with CRISPR-like repeats
阅读文章 HACKER_NEWS
大语言模型
Hacker News
AgentKit MCP 网关上手指南｜让企业存量服务快速接入 AI
阅读文章 JUEJIN
掘金
工程实践
Ringg’s AI agents resolve up to 65% of customer calls with OpenAI
阅读文章 BLOGS_PODCASTS
大语言模型
AI Agent
Gemini 3.8 text-to-speech says hello
阅读文章 HACKER_NEWS
大语言模型
Hacker News
The Download: why AI's latest breakthroughs and fears may be more hype than rea
阅读文章 HACKER_NEWS
AI
Hacker News
Agensh: Scaling Organizational Intelligence to 1,024 Agents
阅读文章 ARXIV
大语言模型
AI Agent
[AINews] Claude Opus 5.5, the new default model for AINews — and everybody cuts prices 40-50%
阅读文章 BLOGS_PODCASTS
大语言模型
AI Agent
Pentagon says overreliance on AI contributed to missile strike on Iran school
阅读文章 HACKER_NEWS
AI
Hacker News
Flash-dLLM: IO-Aware KV Caching and Parallel Decoding for Fast, Memory-Efficient Diffusion LLMs
阅读文章 ARXIV
大语言模型
生成式 AI