close

DEV Community

# llm

Posts

👋 Sign in for the ability to sort posts by relevant, latest, or top.
# How I Found Out 52% of My Knowledge Graph Was Duplicates (and What I Did About It)

# How I Found Out 52% of My Knowledge Graph Was Duplicates (and What I Did About It)

Comments
2 min read
From 1.4 tok/s to 36 tok/s: What Building a Zero-Dependency C LLM Engine Taught Me About DRAM Ceilings

From 1.4 tok/s to 36 tok/s: What Building a Zero-Dependency C LLM Engine Taught Me About DRAM Ceilings

Comments
6 min read
One Go interface, ten LLMs, three transport classes

One Go interface, ten LLMs, three transport classes

Comments
6 min read
How much does context cost an AI coding agent? grep vs graph vs LSP, measured across 936 runs

How much does context cost an AI coding agent? grep vs graph vs LSP, measured across 936 runs

Comments
12 min read
Sipp: a local-first runtime for Hybrid AI Applications

Sipp: a local-first runtime for Hybrid AI Applications

Image Image Image 10
Comments
11 min read
Cli-Modelarium 0.1.4: 10 LLM providers now, with Qwen and GLM

Cli-Modelarium 0.1.4: 10 LLM providers now, with Qwen and GLM

Comments
2 min read
Token economics: from model internals to agent costs

Token economics: from model internals to agent costs

Comments
5 min read
Shipping a Local LLM API with FastAPI and Ollama

Shipping a Local LLM API with FastAPI and Ollama

Comments 1
10 min read
【红杉播客】AI Neolab--Engram【主攻记忆与持续学习】--分享未来 AI 发展趋势的独特见解

【红杉播客】AI Neolab--Engram【主攻记忆与持续学习】--分享未来 AI 发展趋势的独特见解

Comments
2 min read
Why RAG Isn't Enough: Building RationaleVault for Cognitive Continuity

Why RAG Isn't Enough: Building RationaleVault for Cognitive Continuity

Comments
4 min read
The OpenAI API everyone copied isn't the one OpenAI recommends

The OpenAI API everyone copied isn't the one OpenAI recommends

Comments
7 min read
Five ways your AI coding agent wastes tokens (and how to fix each one)

Five ways your AI coding agent wastes tokens (and how to fix each one)

Image 1
Comments
6 min read
I gave my AI agent database access. Then I built a firewall so it couldn't wipe prod.

I gave my AI agent database access. Then I built a firewall so it couldn't wipe prod.

Comments 1
3 min read
Handling Multi-Model API Outages Without Melting Production

Handling Multi-Model API Outages Without Melting Production

Comments
7 min read
I edited a system prompt and had no way to prove it changed anything. So I built a measurement tool.

I edited a system prompt and had no way to prove it changed anything. So I built a measurement tool.

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