DEV Community

# llm

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
Your AI Agent Is Failing Because of Your Data Layer, Not Your Model

Your AI Agent Is Failing Because of Your Data Layer, Not Your Model

2
Comments 1
3 min read
Local Mac Gemma 4 Deployment with MCP and Antigravity CLI

Local Mac Gemma 4 Deployment with MCP and Antigravity CLI

5
Comments
9 min read
I Was Tired of AI Subscriptions, So I Built a Free Local PDF Tutor for Dense Docs

I Was Tired of AI Subscriptions, So I Built a Free Local PDF Tutor for Dense Docs

1
Comments
3 min read
.NET AI Architect Laboratory: Making AI Work and Execute Tools (Phase 2)

.NET AI Architect Laboratory: Making AI Work and Execute Tools (Phase 2)

Comments
2 min read
How Far Can a Small Coding Model Go With a Better Harness?

How Far Can a Small Coding Model Go With a Better Harness?

Comments
10 min read
I spent 5 weeks building an open-source multi-agent orchestrator. The hard part wasn't the agents — it was the memory.

I spent 5 weeks building an open-source multi-agent orchestrator. The hard part wasn't the agents — it was the memory.

2
Comments
8 min read
Building Agentic Laravel Apps with Prism PHP

Building Agentic Laravel Apps with Prism PHP

1
Comments
9 min read
I built an x86_64 kernel from scratch, and it made me hate AI documentation tools. So I built my own.

I built an x86_64 kernel from scratch, and it made me hate AI documentation tools. So I built my own.

Comments
2 min read
.NET AI Architect Laboratory: My Architectural Experiments and Learning Journey in the AI Ecosystem (Phase 1)

.NET AI Architect Laboratory: My Architectural Experiments and Learning Journey in the AI Ecosystem (Phase 1)

Comments
3 min read
KV Cache Explained Like You're an LLM Engineer

KV Cache Explained Like You're an LLM Engineer

Comments
12 min read
Claude Sonnet 4.6 vs GPT-4.1 vs Gemini 2.5 Flash: which wins JSON extraction?

Claude Sonnet 4.6 vs GPT-4.1 vs Gemini 2.5 Flash: which wins JSON extraction?

Comments
3 min read
The 55.8 Percent Productivity Number From Doshi And Vaishnav Is Narrower Than People Think

The 55.8 Percent Productivity Number From Doshi And Vaishnav Is Narrower Than People Think

Comments
2 min read
Retrieval accuracy falls roughly 50% when the answer sits in the middle of a long context window instead of at the edges

Retrieval accuracy falls roughly 50% when the answer sits in the middle of a long context window instead of at the edges

Comments
1 min read
Running Nvidia Nemotron on LangChain via OpenRouter

Running Nvidia Nemotron on LangChain via OpenRouter

Comments
4 min read
I Thought One AI Agent Was Enough. I Ended Up Building Six

I Thought One AI Agent Was Enough. I Ended Up Building Six

2
Comments 2
4 min read
đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.