DEV Community

#llm

Posts

👋 Sign in for the ability to sort posts by relevant, latest, or top.
I Built 4 AI Agent Apps That Run 100% in Your Browser with Laya and WebGPU (No API Key, No Server)

I Built 4 AI Agent Apps That Run 100% in Your Browser with Laya and WebGPU (No API Key, No Server)

Comments
9 min read
My model router taught me that 'frontier' is a marketing tier, not a quality guarantee

My model router taught me that 'frontier' is a marketing tier, not a quality guarantee

1
Comments
2 min read
Capability Parity Is Not an Eval

Capability Parity Is Not an Eval

Comments
4 min read
Build a RAG Chatbot: Connecting an LLM to Your Own Documents

Build a RAG Chatbot: Connecting an LLM to Your Own Documents

Comments
2 min read
How to Build an AI Agent: From One Prompt to a Production Setup

How to Build an AI Agent: From One Prompt to a Production Setup

Comments
4 min read
How to Estimate the Cost per User of an LLM Feature (With a Python Cost Model)

How to Estimate the Cost per User of an LLM Feature (With a Python Cost Model)

Comments
8 min read
Hugging Face Official Benchmarks: Daily Update 2026-11-01

Hugging Face Official Benchmarks: Daily Update 2026-11-01

Comments
5 min read
Building a Zotero AI plugin with a built-in Zotero MCP server — and making every LLM citation clickable back to the exact PDF passage

Building a Zotero AI plugin with a built-in Zotero MCP server — and making every LLM citation clickable back to the exact PDF passage

Comments
6 min read
Prospero is a C++ coding harness for local LLMs whose author claims around two orders of magnitude fewer resources

Prospero is a C++ coding harness for local LLMs whose author claims around two orders of magnitude fewer resources

Comments
3 min read
Бухгалтерия на естественном языке: каким должен быть MCP-сервер. Часть 3

Бухгалтерия на естественном языке: каким должен быть MCP-сервер. Часть 3

Comments
2 min read
Бухгалтерия на естественном языке: каким должен быть MCP-сервер. Часть 2

Бухгалтерия на естественном языке: каким должен быть MCP-сервер. Часть 2

Comments
2 min read
Бухгалтерия на естественном языке: каким должен быть MCP-сервер. Часть 4

Бухгалтерия на естественном языке: каким должен быть MCP-сервер. Часть 4

Comments
1 min read
Your LLM Serving Engine Ships Every 13 Days: Reading vLLM's Breaking-Change Lists as Upgrade Risk Data

Your LLM Serving Engine Ships Every 13 Days: Reading vLLM's Breaking-Change Lists as Upgrade Risk Data

Comments 1
13 min read
LM Studio vs Ollama on an RTX 5080: The Settings Matter More Than the Wrapper

LM Studio vs Ollama on an RTX 5080: The Settings Matter More Than the Wrapper

Comments
5 min read
SWE-Bench Pro Has Two Versions: What the Hugging Face Leaderboard's 47 Rows Mix Together

SWE-Bench Pro Has Two Versions: What the Hugging Face Leaderboard's 47 Rows Mix Together

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