浅析大模型推理十二篇之关键指标
阅读文章 JUEJIN
掘金
工程实践
CHRONOLOGICAL LEDGER
按时间浏览
2026 年
八月
50 ENTRIESHow OneAdvanced deployed over 50 AI agents on UK-sovereign AWS
阅读文章 BLOGS_PODCASTS
大语言模型
RAG
AI is removing the middle class of software engineering
阅读文章 HACKER_NEWS
AI
Hacker News
A Quantum Roadmap for Softmax Attention: Exact Born-Rule Analogs for Softmax Attention on the Probability Simplex
阅读文章 ARXIV
AI
quant-ph
Someone is running mass vulnerability scans, spoofing AI bots like ClaudeBot
阅读文章 HACKER_NEWS
AI
Hacker News
Putting sign language AI into users’ hands
阅读文章 BLOGS_PODCASTS
AI
博客与播客
How to Verify Consistency of Probabilistic Claims
阅读文章 ARXIV
AI
cs.CC
Test-Time Self-Evolving GUI Visual Grounding via Reflection-Guided On-Policy Self-Distillation
阅读文章 ARXIV
AI Agent
计算机视觉
Pay with confidence: How Solv Labs built verifiable, auditable agent payments on Amazon Bedrock AgentCore payments
阅读文章 BLOGS_PODCASTS
AI Agent
Amazon Bedrock AgentCore
Long-Horizon AI Research for Grothendieck Constant: A Case Study in Human-AI Mathematical Collaboration
阅读文章 ARXIV
AI Agent
cs.AI
Launch HN: Discovered Materials (YC P26) – AI agents to discover new materials
阅读文章 HACKER_NEWS
AI Agent
Hacker News
Tim Gowers: What sort of maths are LLMs good at?
阅读文章 HACKER_NEWS
大语言模型
Hacker News
AI Agent 的“自述”不可信：如何构建可取证、可评估、可进化的 Agent 生产流水线？
阅读文章 JUEJIN
AI Agent
掘金
WorkBuddy帮我写了一篇言情叙事小说。
阅读文章 JUEJIN
AI
掘金
[AINews] How to steal a Reasoning Trace
阅读文章 BLOGS_PODCASTS
大语言模型
RAG
llama.cpp
阅读文章 HACKER_NEWS
大语言模型
Hacker News
从零开发一个 Coding Agent（七）：实现纯文本 Agent Loop
阅读文章 JUEJIN
AI Agent
掘金
ConVAWG: A Retrieval-Grounded Framework for Controlled Synthetic Dialogue Generation in Violence Against Women and Girls
阅读文章 ARXIV
大语言模型
cs.CL
Company Offering '100% Human-Written, Never AI' Medical Research Is 100% AI
阅读文章 HACKER_NEWS
AI
Hacker News
Stealing Reasoning Traces from Proprietary LLM APIs
阅读文章 ARXIV
大语言模型
Prompt 工程
Daybreak models are now available on AWS
阅读文章 BLOGS_PODCASTS
AI
Product
Suzanne: AI tool for designing and manufacturing physical products
阅读文章 HACKER_NEWS
AI
Hacker News
Sci-VBench: Evaluating Knowledge- and Reasoning-Intensive Video Generation in Science Domains
阅读文章 ARXIV
计算机视觉
Prompt 工程
🔬The BioAI Phase Shift - Matthew McPartlon & Neil Patil, Chai Discovery
阅读文章 BLOGS_PODCASTS
大语言模型
博客与播客
Accelerate cyber defense with OpenAI and AWS: Daybreak Red & Daybreak Blue now available to eligible customers on Amazon Bedrock
阅读文章 BLOGS_PODCASTS
大语言模型
AI Agent
Deploying Anthropic Claude apps gateway for AWS for enterprise workloads
阅读文章 BLOGS_PODCASTS
大语言模型
AI Agent
ArchAgent v2: A Case Study with the Data Prefetching Championship
阅读文章 ARXIV
AI Agent
cs.AI
OpenAI’s head of ethics leaves less than a year after joining
阅读文章 HACKER_NEWS
AI
Hacker News
First Orion accelerates QA automation using Amazon Nova Act
阅读文章 BLOGS_PODCASTS
AI Agent
生成式 AI
Energy-Structured Latent World Models with Neural Time Fields for Physically Constistent Open-World Motion Planning
阅读文章 ARXIV
AI
cs.RO
Why Go Is an Ideal Language for AI-Assisted Software Engineering
阅读文章 HACKER_NEWS
AI
Hacker News
How ONESTRUCTION built the Ishigaki-IDS foundation model with AWS GenAIIC
阅读文章 BLOGS_PODCASTS
大语言模型
AI Agent
Financial Numerical Prediction and Allocation as Token Generation
阅读文章 ARXIV
计算机视觉
cs.CV
What I learned by putting GitHub Copilot behind a MitM proxy
阅读文章 HACKER_NEWS
AI
Hacker News
SHE: Trajectory-driven Safety Harness Evolution for LLM Agents
阅读文章 ARXIV
大语言模型
AI Agent
AMIE, our research medical AI system, demonstrates real-time clinical video consultation capabilities in a first-of-its-kind study.
阅读文章 BLOGS_PODCASTS
AI
Google Health
番外篇二：《不到十行代码，我用ReactAgen搭了个会自己调工具的 Agent》
阅读文章 JUEJIN
AI Agent
掘金
Stealing Reasoning Traces from Proprietary LLM APIs
阅读文章 HACKER_NEWS
大语言模型
Hacker News
Space-Creating versus Dead Possession: An Off-Ball Possession-Quality Index for Broadcast Football
阅读文章 ARXIV
计算机视觉
cs.CV
How Pixieset achieved 35% AI feature adoption by solving the right problem with Amazon Bedrock
阅读文章 BLOGS_PODCASTS
大语言模型
AI Agent
Consilience for Verifier-Free Test-Time Scaling
阅读文章 ARXIV
大语言模型
cs.CL
Apple Silicon and macOS VMs: 11–16× Faster LLM Inference with Llama.cpp
阅读文章 HACKER_NEWS
大语言模型
Hacker News
How to organize Claude Code for product work
阅读文章 HACKER_NEWS
大语言模型
Hacker News
Decoding-Level Taboo: A Diagnostic Stress Test for LLM Robustness
阅读文章 ARXIV
大语言模型
Prompt 工程
DSLE: A Learning Environment for Dark Souls Boss Encounters
阅读文章 ARXIV
AI Agent
cs.AI
手写一个 LLM Harness 框架：用工程化手段把大模型幻觉踩在脚下
阅读文章 JUEJIN
掘金
工程实践
GENCO - A Unified Neural Solver Embedded in a Development Framework for Steady-State Grid Analysis
阅读文章 ARXIV
AI
cs.AI
The Water Footprint of AI
阅读文章 HACKER_NEWS
AI
Hacker News