#RAG

Mastodon discussion Apr 7

📰 Bağlam Mühendisliği 2026: Yapay Zekâ Ajanlarının RAG’i Yerini Aldığı Anahtar TeknikYapay zekâ ajanlarının performansın...

📰 Bağlam Mühendisliği 2026: Yapay Zekâ Ajanlarının RAG’i Yerini Aldığı Anahtar TeknikYapay zekâ ajanlarının performansını değiştiren en kritik faktör, veri değil, bağlam. 2025-2026...

RAG

9

Mastodon discussion Apr 7

仕事来ましたです【海外記事紹介】Karpathy氏「RAGはもう古い」—LLMが自動管理する永続的知識ベースの衝撃 https://techfeed.io/entries/69d38f4ed66ba515c3956d6b#Apple #LL...

仕事来ましたです【海外記事紹介】Karpathy氏「RAGはもう古い」—LLMが自動管理する永続的知識ベースの衝撃 https://techfeed.io/entries/69d38f4ed66ba515c3956d6b#Apple #LLM #news #bot

LLM RAG

24

Mastodon discussion Apr 7

#Tech #AI #ML What the Bits-over-Random Metric Changed in How I Think About RAG and Agents https://towardsdatascience.co...

#Tech #AI #ML What the Bits-over-Random Metric Changed in How I Think About RAG and Agents https://towardsdatascience.com/what-the-bits-over-random-metric-changed-in-how-i-think-ab...

RAG

27

Mastodon discussion Apr 7

Stop losing your AI chat context. I just published a technical teardown of MemPalace—a 100% local, RAG-killer memory arc...

Stop losing your AI chat context. I just published a technical teardown of MemPalace—a 100% local, RAG-killer memory architecture by @bensig & @MillaJovovich using 30x AAAK compres...

RAG

18

Dev.to tutorial Apr 7

RAGの検索精度を3軸で測ったら最適解が条件で全く変わった

RAGの検索精度を3軸で測ったら最適解が条件で全く変わった RAG（Retrieval-Augmented...

RAG

12

Mastodon discussion Apr 6

Min Choi (@minchoi)Karpathy의 ‘Second Brain’ 아이디어를 바탕으로, LLM이 논문·저장소·노트를 살아 있는 위키처럼 계속 업데이트하며 더 똑똑해지는 방식이 소개됐다. 기존 RAG를 넘...

Min Choi (@minchoi)Karpathy의 ‘Second Brain’ 아이디어를 바탕으로, LLM이 논문·저장소·노트를 살아 있는 위키처럼 계속 업데이트하며 더 똑똑해지는 방식이 소개됐다. 기존 RAG를 넘어서는 활용으로, 다양한 실제 사용 사례 10가지를 예고하며 혁신적 AI 응용 가능성을 강조한다.https:...

LLM RAG

18

Mastodon discussion Apr 6

Building a Lightweight RAG Pipeline (Node.js + JSONL) https://www.himpfen.com/building-lightweight-rag-pipeline-nodejs-j...

Building a Lightweight RAG Pipeline (Node.js + JSONL) https://www.himpfen.com/building-lightweight-rag-pipeline-nodejs-jsonl/#ai #rag #nodejs #programming

RAG

24

Mastodon discussion Apr 6

📰 RAGの最適化手法が多すぎて迷子になったので、整理したら全体像が見えた (👍 19)🇬🇧 A map of the RAG optimization landscape, organizing techniques like multi...

📰 RAGの最適化手法が多すぎて迷子になったので、整理したら全体像が見えた (👍 19)🇬🇧 A map of the RAG optimization landscape, organizing techniques like multi-query, fusion, decomposition, and reranking into a clearer ...

RAG

9

Mastodon discussion Apr 5

📰 Proxy-Pointer RAG Delivers 92% Accuracy Without Vector Databases (2026 Breakthrough)A groundbreaking approach called P...

📰 Proxy-Pointer RAG Delivers 92% Accuracy Without Vector Databases (2026 Breakthrough)A groundbreaking approach called Proxy-Pointer RAG delivers vector RAG-scale accuracy without ...

RAG

9

Mastodon discussion Apr 5

📰 Proxy-Pointer RAG: 98.7% Doğrulukla Vektör Veritabanlarını Yerini Alıyor | 2026 Microsoft Doğrula...Yeni bir RAG tekno...

📰 Proxy-Pointer RAG: 98.7% Doğrulukla Vektör Veritabanlarını Yerini Alıyor | 2026 Microsoft Doğrula...Yeni bir RAG teknolojisi, vektör veritabanları olmadan geleneksel vektör RAG'l...

Microsoft RAG

9

Dev.to tutorial Apr 5

Embedding "xương sống" của RAG

Xây mô hình embedding theo miền trong chưa đến một ngày: hướng fine-tune để cải thiện truy...

RAG

12

Mastodon discussion Apr 5

Hermesについては、タムズでもしっかり話し合っておかないとKarpathy shares 'LLM Knowledge Base' architecture that bypasses RAG with an evolving mark...

Hermesについては、タムズでもしっかり話し合っておかないとKarpathy shares 'LLM Knowledge Base' architecture that bypasses RAG with an evolving markdown library maintained by AI https://venturebeat.com/data/k...

LLM RAG

27

Mastodon discussion Apr 5

Spent 3 hours debugging why my RAG system was returning garbage. Turned out the chunking was splitting sentences mid-wor...

Spent 3 hours debugging why my RAG system was returning garbage. Turned out the chunking was splitting sentences mid-word. Three hours. For a split() call.AI engineering is humblin...

RAG

18

Dev.to tutorial Apr 5

A Vectorless RAG System for Smarter Document Intelligence

Modern AI applications rely heavily on Retrieval-Augmented Generation (RAG) to analyze documents and...

RAG

33

Mastodon discussion Apr 4

RAG isn't dead — you're just doing it wrong.90% of RAG implementations fail because they treat it as "stuff context in p...

RAG isn't dead — you're just doing it wrong.90% of RAG implementations fail because they treat it as "stuff context in prompt." Here's what actually works in production.https://tel...

RAG

18

Mastodon discussion Apr 4

RAG isn't dead — you're just doing it wrong.90% of RAG implementations fail because they treat it as 'stuff context in p...

RAG isn't dead — you're just doing it wrong.90% of RAG implementations fail because they treat it as 'stuff context in prompt.' Here's what actually works in production.https://tel...

RAG

24

Mastodon discussion Apr 4

We replaced RAG with a virtual filesystem for our AI documentation assistanthttps://www.mintlify.com/blog/how-we-built-a...

We replaced RAG with a virtual filesystem for our AI documentation assistanthttps://www.mintlify.com/blog/how-we-built-a-virtual-filesystem-for-our-assistant#ai

RAG

18

Dev.to tutorial Apr 4

Why RAG Falls Short for Documentation Search (and What to Try Instead)

RAG struggles with structured documentation. Learn how a virtual filesystem approach lets LLMs navigate docs like developers, producing better multi-page answers.

RAG

12

Mastodon discussion Apr 4

📰 How Coding Agents Outperform RAG: Tools, Memory & Repo Context (2026)The components of a coding agent—tools, memory, a...

📰 How Coding Agents Outperform RAG: Tools, Memory & Repo Context (2026)The components of a coding agent—tools, memory, and repository context—are revolutionizing how LLMs generate ...

RAG

9

Mastodon discussion Apr 4

Akshay (@akshay_pachaar)AI 엔지니어를 위한 8가지 RAG 아키텍처를 소개하며, Naive RAG부터 다양한 검색·생성 조합 패턴까지 용도별로 설명한다. RAG 시스템 설계와 구현을 고민하는 개발...

Akshay (@akshay_pachaar)AI 엔지니어를 위한 8가지 RAG 아키텍처를 소개하며, Naive RAG부터 다양한 검색·생성 조합 패턴까지 용도별로 설명한다. RAG 시스템 설계와 구현을 고민하는 개발자에게 실용적인 참고 자료다.https://x.com/akshay_pachaar/status/20400504...

RAG

9

Mastodon discussion Apr 4

📰 Singaporean Developer Builds AI Legal Assistant Using RAG with Triple-Model FailoverA Singaporean developer has create...

📰 Singaporean Developer Builds AI Legal Assistant Using RAG with Triple-Model FailoverA Singaporean developer has created a cutting-edge RAG-powered legal assistant with a triple-A...

RAG API

9

Mastodon discussion Apr 4

📰 Singapurlu Geliştirici, RAG Kullanarak Yapay Zeka Hukuk Asistanı GeliştirdiSingapurlu bir yazılım geliştirici, yerel h...

📰 Singapurlu Geliştirici, RAG Kullanarak Yapay Zeka Hukuk Asistanı GeliştirdiSingapurlu bir yazılım geliştirici, yerel hukuk sistemine derinlemesine entegre edilmiş, üçlü yapay zek...

RAG

9

Mastodon discussion Apr 4

📰 RAG Basics: What Is Retrieval-Augmented Generation and Why It Matters?Retrieval-Augmented Generation (RAG) is a breakt...

📰 RAG Basics: What Is Retrieval-Augmented Generation and Why It Matters?Retrieval-Augmented Generation (RAG) is a breakthrough AI design pattern that overcomes the static knowledge...

RAG

9

Mastodon discussion Apr 4

📰 RAG Temelleri: Retrieval-Augmented Generation Nedir ve Neden Önemli?Retrieval-Augmented Generation (RAG), yapay zekanı...

📰 RAG Temelleri: Retrieval-Augmented Generation Nedir ve Neden Önemli?Retrieval-Augmented Generation (RAG), yapay zekanın sınırlı bilgiye sahip olma sorununu çözmek için geliştiril...

RAG

9