📄 文章列表

52 篇文章
cn_ai

Harness 已经很准了，为什么还需要一个 Agent Native Database

❌ failed ⭐ ☆☆☆☆☆ 2026-11-09
TDS

I Told an AI Agent That Its Wrong Answers Were Right. One Model Believed Me.

✅ completed ⭐ ☆☆☆☆☆ 2026-10-31
TDS

I Broke a Browser Agent on Purpose. Spotting the Fault Was Not the Same as Fixing It

✅ completed ⭐ ☆☆☆☆☆ 2026-10-28
TDS

Your RAG Pipeline Is Missing a 1994 Algorithm

✅ completed ⭐ ☆☆☆☆☆ 2026-10-28
TDS

I Tested Four Ways to Give an AI Assistant a Memory. The Obvious One Was the Worst Value.

✅ completed ⭐ ☆☆☆☆☆ 2026-10-15
TDS

I Built a Trap for AI Image Judges. They Walked Into a Different One.

✅ completed ⭐ ☆☆☆☆☆ 2026-10-12
TDS

AI Slop Is Already in Your Training Dataset. I Tested Three Ways to Spot It.

✅ completed ⭐ ☆☆☆☆☆ 2026-09-27
TDS

FAQ as RAG: When You Get to Design the Corpus

✅ completed ⭐ ☆☆☆☆☆ 2026-09-01
TDS

5 AI Skills That Will Keep Data Scientists Relevant in 2027

✅ completed ⭐ ☆☆☆☆☆ 2026-09-01
TDS

Why RAG Complexity Should Be Earned

✅ completed ⭐ ☆☆☆☆☆ 2026-08-31
TDS

Noisy Text in RAG: Typos, OCR, and the Gap Classical Spell-Check Leaves

✅ completed ⭐ ☆☆☆☆☆ 2026-08-30
TDS

Designing a Persistent Knowledge Layer That Refuses to Guess

✅ completed ⭐ ☆☆☆☆☆ 2026-08-16
TDS

How I Reproduced BM25, Dense Retrieval, and SPLADE on a 16GB MacBook

✅ completed ⭐ ☆☆☆☆☆ 2026-07-27
TDS

The Untaught Lessons of RAG Retrieval: Cosine Is Not the Foundation

✅ completed ⭐ ☆☆☆☆☆ 2026-07-03
TDS

How Far Can Classical NLP Go? From Bag-of-Words to Stacking on Spooky Author Identification

✅ completed ⭐ ☆☆☆☆☆ 2026-06-29
TDS

An LLM as arbiter in RAG retrieval: picking the right candidate with reasons

✅ completed ⭐ ★★★☆☆ 2026-06-25
TDS

Anchor Detection for RAG: Parallel Detectors, Then One LLM Call at the End

✅ completed ⭐ ★★★☆☆ 2026-06-24
TDS

Retrieval Augmented Generation (RAG) — An Introduction

✅ completed ⭐ ★★★★★★ 2025-04-21
TDS

A Practical Guide to BERTopic for Transformer-Based Topic Modeling

✅ completed ⭐ ★★★★★★ 2025-05-08
TDS

Agentic RAG Applications: Company Knowledge Slack Agents

✅ completed ⭐ ★★★★★★ 2025-05-30