DEV Community

# llm

Posts

👋 Sign in for the ability to sort posts by relevant, latest, or top.
Your LLM Isn't the Problem. Your Pipeline Is.

Your LLM Isn't the Problem. Your Pipeline Is.

Comments
4 min read
Stop Building AI Wrappers. Start Building AI Products.

Stop Building AI Wrappers. Start Building AI Products.

1
Comments
2 min read
What an AI does when nobody on the line is human (two case studies)

What an AI does when nobody on the line is human (two case studies)

2
Comments
7 min read
How I Escaped Claude & Cursor Limits: The Ultimate Free Local AI Coding Setup with Ollama + Continue.dev (2026 Guide)

How I Escaped Claude & Cursor Limits: The Ultimate Free Local AI Coding Setup with Ollama + Continue.dev (2026 Guide)

5
Comments 2
4 min read
The model was never the problem. The context was

The model was never the problem. The context was

Comments
5 min read
Qwen 3.6 27B Arrives with GGUF, llama.cpp Powers Local Multimodal

Qwen 3.6 27B Arrives with GGUF, llama.cpp Powers Local Multimodal

Comments
4 min read
The Representation Problem: Why RAG vs. Agentic Search Is the Wrong Debate

The Representation Problem: Why RAG vs. Agentic Search Is the Wrong Debate

Comments 1
17 min read
I Tested Three AI Memory Retrieval Strategies. The Hard Failure Was Semantic

I Tested Three AI Memory Retrieval Strategies. The Hard Failure Was Semantic

Comments
8 min read
Lovable's 48-Day Silent Breach Shows Why AI Platforms Need Audit Trails, Not Just Bug Bounties

Lovable's 48-Day Silent Breach Shows Why AI Platforms Need Audit Trails, Not Just Bug Bounties

Comments
9 min read
AI 週報:2026/04/17–04/24 OpenAI 一週連發、Anthropic 撞翻 Figma、Mythos 進入政治場

AI 週報:2026/04/17–04/24 OpenAI 一週連發、Anthropic 撞翻 Figma、Mythos 進入政治場

Comments 1
4 min read
12 million tokens, linear cost: Subquadratic's bet against the attention tax

12 million tokens, linear cost: Subquadratic's bet against the attention tax

Comments
3 min read
Run your first AI agent in Java — for free, with Mistral

Run your first AI agent in Java — for free, with Mistral

2
Comments
2 min read
Promptfoo is a CI gate, not an eval framework. Treating it like one cost us $4,200

Promptfoo is a CI gate, not an eval framework. Treating it like one cost us $4,200

Comments 1
4 min read
Beyond the "Brute Force Beauty": A Modular, Brain-Inspired LLM Architecture (Thoughts on grand models: Part 3)

Beyond the "Brute Force Beauty": A Modular, Brain-Inspired LLM Architecture (Thoughts on grand models: Part 3)

Comments
7 min read
Claude Code's plan mode is prompt engineering, not hard enforcement

Claude Code's plan mode is prompt engineering, not hard enforcement

Comments 1
4 min read
👋 Sign in for the ability to sort posts by relevant, latest, or top.