DEV Community

# llm

Posts

👋 Sign in for the ability to sort posts by relevant, latest, or top.
When Your LLM Provider Pulls the Rug: Lessons from Anthropic's OAuth Shutdown

When Your LLM Provider Pulls the Rug: Lessons from Anthropic's OAuth Shutdown

Comments
2 min read
Stop prompting "write me an API" — teach the LLM the shape first

Stop prompting "write me an API" — teach the LLM the shape first

Comments
2 min read
From Tokens to Attention: My First Real Mental Model of LLMs

From Tokens to Attention: My First Real Mental Model of LLMs

1
Comments 2
5 min read
What I Learned Building with Gemma 4

Gemma 4 Challenge: Write about Gemma 4 Submission

What I Learned Building with Gemma 4

4
Comments
4 min read
llama.cpp Speculative Checkpointing, Ollama Multimodal Tool, MLX vs GGUF for Gemma 4

llama.cpp Speculative Checkpointing, Ollama Multimodal Tool, MLX vs GGUF for Gemma 4

Comments
4 min read
Beyond the Prompt: Understanding "Agent Skills" as Dynamic Context Management

Beyond the Prompt: Understanding "Agent Skills" as Dynamic Context Management

Comments
4 min read
What Is LangGraph? A Beginner-Friendly Introduction

What Is LangGraph? A Beginner-Friendly Introduction

1
Comments
2 min read
The Model Doesn't Matter. The Harness Does.

The Model Doesn't Matter. The Harness Does.

Comments
4 min read
Prompt Engineering is Not Enough: Where Software Architecture Takes Over

Prompt Engineering is Not Enough: Where Software Architecture Takes Over

Comments
1 min read
From ChatGPT System Prompt to a Music App

From ChatGPT System Prompt to a Music App

Comments
4 min read
Why Much AI Memory Risks Rotting — The Exception Is the Memory of Being Wrong

Why Much AI Memory Risks Rotting — The Exception Is the Memory of Being Wrong

Comments
11 min read
Your AI's Persona Is a String. A New Paper Argues It Should Be a Steering Vector.

Your AI's Persona Is a String. A New Paper Argues It Should Be a Steering Vector.

Comments
7 min read
Two DM-origin problems, not one: security hardening vs. compliance-bias hardening

Two DM-origin problems, not one: security hardening vs. compliance-bias hardening

Comments
3 min read
Qwen3.6, and WilmerAI OpenCode workflows

Qwen3.6, and WilmerAI OpenCode workflows

Comments
3 min read
Benchmark Results: SmolLM3 3B, Phi-4-mini, DeepSeek V4, Grok 4.20 — Agent Coding Tested

Benchmark Results: SmolLM3 3B, Phi-4-mini, DeepSeek V4, Grok 4.20 — Agent Coding Tested

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