AI 教程与实战

A 27B model on my own GPU audited my Splunk and Sysmon install with zero cloud: 10 real findings, and it fixed some of them itself, including two false positives from its own earlier audits.

Debug algorithmic trading backtests with Python: catch look-ahead bias, compare complex models fairly, and test execution costs and order failures.

I started this experiment for a slightly different reason. I was playing with a system that could...

Everybody's shipping AI agents. Nobody's auditing their toolchains. The MCP (Model Context Protocol)...

开发者推出一个社区站点，供工程师和创作者分享各自的 AI 工具、工作流与配置，并保持自己的配置随时更新、便于分享给朋友和同事。发起人表示自己也没完全搞明白 AI 配置，希望借此看到别人在用什么工具、为什么换用某个 agent harness、在用哪些技能。

A model predicts a 92% risk of hospital readmission. The SHAP values show age, prior admissions, and...

Large language models have become remarkably capable. With enough parameters, data, and training,...

Explore why developers are shifting to local-first AI, privacy-focused hardware, and edge computing in 2026 over traditional cloud platforms.

有人试过让 Astra 和 Fable 就完美风格指南达成一致吗？然后用 web mcp 把它托管在某处。

That's a working React app. Sidebar navigation with active states, four KPI cards, two charts, and a...

i'm jon, i co-founded backboard.io. this is a launch post. it's short and there's code. video models...

TypeSafe's Jev is an odd one. It isn't a chat model - you send a state plus typed questions (Choice /...

I stored passwords in plaintext on a floppy disk in the 1980s. Recently, a coding agent made a...

Your Markdown can be perfectly rendered and completely wrong Markdown has an unfair...

Federal Reserve Chair Kevin Warsh singled out AI debt issuance as a driver behind the 10-year Treasury yield crossing 5 percent. Here is how the feedback loop works.

KAIST EvolveTrade shows that frozen LLM trading agents improve Sharpe ratio not by writing new strategies, but by letting policy refinement turn Python outputs into explicit allocation math.

Keras 3 如何帮助 Expedia 的排序栈实现现代化 https://medium.com/expedia-group-tech/how-keras-3-helped-modernise-expedia-groups-lodging-ranking-stack-7fec96f052fd

Six weeks with the Pocket AI recorder: meeting action items, voice-memo idea capture, personal logistics, and its MCP server wired into Claude Code.

A read-only scanner that fingerprints MCP on both transports and sorts every endpoint into open, protected, or out of spec. Four postures, one...

I kept running into the same failure mode when switching between AI workers, browser sessions, or...

NVIDIA 推出 AIPerf，作为 GenAI-Perf 的指定继任者并从零重写，采用多进程架构与 ZMQ 协调，避免客户端成为压测瓶颈。它支持 15+ 端点类型、ShareGPT 等公开数据集以及 Mooncake、Baseten、WEKA（AgentX）的 trace 回放格式，并提供 constant、Poisson、gamma 到达模式与并发、请求速率渐进爬坡。

Lucius AI 用 AlloyDB for PostgreSQL 承载超 21 万条招标数据，将语义搜索迁移到 ScaNN 索引后，代表性生产查询延迟从 1.14 秒降至 24 毫秒，提速 47 倍。该平台还通过 MCP 将 AI 智能体接入数据库，在仅授予 SELECT 和单表 UPDATE 的最小权限下自动完成查询分析、数据新鲜度检查与事故取证。

A $52 to $3,292 token-launch bot, an $89 to $7,769 six-agent trading desk, a stablecoin arbitrage, and two more. What on-chain data, fee schedules and the authors' own demos actually show.

Since August 2, 2026, Claude embeds a statistical watermark in its text output, and Anthropic's...

Most AI features don't fail in the model. They fail at the gate. Someone demos a shiny prompt....

Included Health 基于 Deep Agents、LangGraph 和 LangSmith 构建了医疗导航智能体 Dot，支持人工接管与临床监督。该智能体采用联邦式架构，用于医疗场景下的导航服务。

It was a Tuesday morning. My OpenCode session had 378,755 tokens of context — weeks of trading-bot...

Semrush has published a focused study on a critical question for companies seeking visibility in...

Every week brings a fresh cycle of tech Twitter arguing whether Artificial General Intelligence (AGI)...

智谱发布长文，详解 GLM-5.3 驱动的 Infra Agent 如何在 10 万+ 国产 AI 加速器集群上从零构建 GLM-5.3-Flash 的生产级推理服务，不到两周将端到端吞吐提升约 3 倍。

I burned a cloud IP address doing AI safety testing. Then I moved the whole operation onto a...

tldr; I asked Claude Fable (in plan mode) to screen record and create cool demo videos for my...

I recently faced an interesting challenge while managing a fleet of IoT devices in Kenya. Managing...

TL;DR Most AI agents re‑read transcripts instead of learning principles, so they repeat...

微软分享了其自身 AI 转型的经验，指出行业讨论已从"AI 能做什么"转向"企业如何用 AI 创造业务价值并拓展人的能力边界"。微软认为，能够成功的组织将是其所称的"前沿企业（Frontier Firms）"。

Databricks 资本市场 GTM 全球负责人 Andrea DeSosa 指出，交易生命周期现代化的关键不是孤立模型，而是把订单、成交、持仓、研究、风险与客户等专有数据在受治理前提下打通。她建议从执行质量、敞口分析和结算异常等高价值决策入手，并提到欧洲 T+1 结算定于 2027 年 10 月 11 日，使准备工作成为近期优先事项。

Every multi-tenant B2B SaaS platform I've worked on eventually converges on the same authorization...

Last week I gave an AI agent a simple job: look at a sales pipeline and tell me what it is worth. It...

AYi 整理 SpaceXAI 团队 @shubgaur 在 Founders 专场 GTM 与客服场的一手实录，提炼出 10 条搭建 AI Bot 业务团队的实战军规。核心路径是先按一职一 Bot 搭班子并设参谋长分发任务，再把重复工作挂在时钟上自动跑，最后守住红线：外发默认草稿、敏感操作必须人审，客服权限按只读、草稿、受控执行逐步放开。

I spent a day reading 45 platform terms of service end to end, because an agent I run kept failing at...