close

Forem

# llm

Posts

👋 Sign in for the ability to sort posts by relevant, latest, or top.
RAG系统实战:从Chunk切分到检索增强全流程解析

RAG系统实战:从Chunk切分到检索增强全流程解析

Image 1
Comments
1 min read
Why Token Counting in Multi-LLM Systems Is Harder Than You Think
Cover image for Why Token Counting in Multi-LLM Systems Is Harder Than You Think

Why Token Counting in Multi-LLM Systems Is Harder Than You Think

Comments
2 min read
AI Data Residency: When Cloud APIs Don't Meet Your Compliance Requirements
Cover image for AI Data Residency: When Cloud APIs Don't Meet Your Compliance Requirements

AI Data Residency: When Cloud APIs Don't Meet Your Compliance Requirements

Comments
15 min read
Why Book Translation Needs a Second Pass

Why Book Translation Needs a Second Pass

Comments
1 min read
I let my AI agent read a file. It tried to leak my credentials.
Cover image for I let my AI agent read a file. It tried to leak my credentials.

I let my AI agent read a file. It tried to leak my credentials.

Image 1
Comments
4 min read
SLMs vs LLMs: Why Smaller Models Are Winning for Specific Business Tasks

SLMs vs LLMs: Why Smaller Models Are Winning for Specific Business Tasks

Comments
7 min read
I ran 5 social engineering attacks on AI. The failure modes are human.

I ran 5 social engineering attacks on AI. The failure modes are human.

Image 1
Comments
2 min read
RAG From First Principles: Why Every AI App Retrieves Before It Generates

RAG From First Principles: Why Every AI App Retrieves Before It Generates

Image 2
Comments
7 min read
Local MCP Server en 15 minutos (y qué hacer con él después)
Cover image for Local MCP Server en 15 minutos (y qué hacer con él después)

Local MCP Server en 15 minutos (y qué hacer con él después)

Comments
8 min read
AI Agents Are Failing Because of This?

AI Agents Are Failing Because of This?

Image 1
Comments
1 min read
Anthropic Silently Dropped Prompt Cache TTL from 1 Hour to 5 Minutes

Anthropic Silently Dropped Prompt Cache TTL from 1 Hour to 5 Minutes

Comments
3 min read
GN: Domain-Adaptive Lossless Compression for LLM Conversation Streams

GN: Domain-Adaptive Lossless Compression for LLM Conversation Streams

Comments
6 min read
Why Search-Enabled LLMs Still Get Numbers Wrong

Why Search-Enabled LLMs Still Get Numbers Wrong

Comments
2 min read
AI Doesn’t Think — It Reflects What We’ve Already Put Online

AI Doesn’t Think — It Reflects What We’ve Already Put Online

Comments
3 min read
How I'd Design a Memory System for an AI Companion App
Cover image for How I'd Design a Memory System for an AI Companion App

How I'd Design a Memory System for an AI Companion App

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