DEV Community

#llm

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
Building docapi: A Reliable Document Extraction Platform for AI Agents

Building docapi: A Reliable Document Extraction Platform for AI Agents

Comments
2 min read
A Four-Type Framework for LLM Wiki by karpathy

A Four-Type Framework for LLM Wiki by karpathy

Comments
4 min read
Building Smarter AI Agents with Hindsight and Cascadeflow: Lessons from Developing an AI Incident Response Assistant

Building Smarter AI Agents with Hindsight and Cascadeflow: Lessons from Developing an AI Incident Response Assistant

2
Comments
5 min read
Kimi K3 vs Claude Fable 5 and Opus 4.8: a benchmark you can run yourself

Kimi K3 vs Claude Fable 5 and Opus 4.8: a benchmark you can run yourself

Comments
7 min read
ELI5 - What is agentic AI?

ELI5 - What is agentic AI?

Comments
2 min read
What Happens When Every Prompt Slot Says Something Different

What Happens When Every Prompt Slot Says Something Different

Comments
6 min read
Series: "Can You Build an Alternative to LLMs? 8 Months of Experiments, 200 Failures, and One Wall" 1

Series: "Can You Build an Alternative to LLMs? 8 Months of Experiments, 200 Failures, and One Wall" 1

1
Comments 2
8 min read
Do Anthropic's Six Agent Design Patterns Still Hold Up in 2026?

Do Anthropic's Six Agent Design Patterns Still Hold Up in 2026?

Comments
5 min read
Setting Up a Local AI Coding Agent with Ollama and Aider (part 4)

Setting Up a Local AI Coding Agent with Ollama and Aider (part 4)

Comments
3 min read
OpenRouter solved one problem. I still had four more

Unpredictable pricing hurts app builders

OpenRouter solved one problem. I still had four more

18
Comments 5
2 min read
Qwen-AgentWorld Trains a Language Model as a World Model for RL Agents: World Model as a Decoupled RL Simulator

Qwen-AgentWorld Trains a Language Model as a World Model for RL Agents: World Model as a Decoupled RL Simulator

Comments
6 min read
AI Agent Guardrails: A Practical Checklist

AI Agent Guardrails: A Practical Checklist

2
Comments 1
8 min read
Your AI agent's leak risk depends more on the model than the prompt

Your AI agent's leak risk depends more on the model than the prompt

Comments
5 min read
Chrome Shrunk a 30,000 Token Web Page Into 300 Tokens.

Chrome Shrunk a 30,000 Token Web Page Into 300 Tokens.

Comments
5 min read
A flat per-call endpoint for summarize / classify / extract in your n8n and Make automations

A flat per-call endpoint for summarize / classify / extract in your n8n and Make automations

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