Forem

# llm

Posts

👋 Sign in for the ability to sort posts by relevant, latest, or top.
AI 週報 — 2026/04/10–2026/04/17 模型封鎖潮來了,但工具鏈才是真戰場
Cover image for AI 週報 — 2026/04/10–2026/04/17 模型封鎖潮來了,但工具鏈才是真戰場

AI 週報 — 2026/04/10–2026/04/17 模型封鎖潮來了,但工具鏈才是真戰場

Comments
1 min read
SambaNova: GPU-Free AI Inference at 5x Speed — AI University Update (78 Providers)

SambaNova: GPU-Free AI Inference at 5x Speed — AI University Update (78 Providers)

1
Comments
2 min read
Ruby is all you need (Part II)
Cover image for Ruby is all you need (Part II)

Ruby is all you need (Part II)

Comments
5 min read
Model Context Protocol en Producción: Por Qué el 80% de los Agentes AI Fallan Antes de los 30 Días
Cover image for Model Context Protocol en Producción: Por Qué el 80% de los Agentes AI Fallan Antes de los 30 Días

Model Context Protocol en Producción: Por Qué el 80% de los Agentes AI Fallan Antes de los 30 Días

Comments
5 min read
Benchmarking Memoria on LongMemEval: Strong Memory Retrieval, Clear Reader Separation

Benchmarking Memoria on LongMemEval: Strong Memory Retrieval, Clear Reader Separation

Comments
7 min read
llms.txt Is Just a Table of Contents. Most AI Tools Stop There.
Cover image for llms.txt Is Just a Table of Contents. Most AI Tools Stop There.

llms.txt Is Just a Table of Contents. Most AI Tools Stop There.

1
Comments
5 min read
How to Serve Mistral Medium 3.5 128B Without Running Out of GPU Memory
Cover image for How to Serve Mistral Medium 3.5 128B Without Running Out of GPU Memory

How to Serve Mistral Medium 3.5 128B Without Running Out of GPU Memory

2
Comments
5 min read
Trust the construct, not the model
Cover image for Trust the construct, not the model

Trust the construct, not the model

1
Comments
7 min read
TradeMemory An AI-Powered Persistence Layer for Disciplined Trading

TradeMemory An AI-Powered Persistence Layer for Disciplined Trading

1
Comments
4 min read
How Smart Model Routing Picks the Right AI for Your Programming Language

How Smart Model Routing Picks the Right AI for Your Programming Language

1
Comments
6 min read
RAG chunking strategy that beats "smarter" alternatives
Cover image for RAG chunking strategy that beats "smarter" alternatives

RAG chunking strategy that beats "smarter" alternatives

Comments
4 min read
Wallet Auth for LlamaIndex: Condition-Based Access for AI Agents
Cover image for Wallet Auth for LlamaIndex: Condition-Based Access for AI Agents

Wallet Auth for LlamaIndex: Condition-Based Access for AI Agents

Comments
5 min read
How to Build a Multi-Agent Pipeline That Doesn't Lose the Plot

How to Build a Multi-Agent Pipeline That Doesn't Lose the Plot

Comments
4 min read
Prompting vs RAG vs Fine-Tuning: When to Use Each (A Developer's Decision Framework)

Prompting vs RAG vs Fine-Tuning: When to Use Each (A Developer's Decision Framework)

Comments
9 min read
Why I Modelled My LLM Pipeline as a DAG Instead of a Chain — and What I Found Out

Why I Modelled My LLM Pipeline as a DAG Instead of a Chain — and What I Found Out

Comments
2 min read
👋 Sign in for the ability to sort posts by relevant, latest, or top.