DEV Community

#llm

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
Still Picking API vs Local LLM by Gut Feeling? A Framework With Real Benchmarks

Still Picking API vs Local LLM by Gut Feeling? A Framework With Real Benchmarks

Comments
6 min read
The Context Window Lie: Why Your LLM Remembers Nothing

The Context Window Lie: Why Your LLM Remembers Nothing

2
Comments
5 min read
Local LLM Video Captioning: Private, Powerful, Open-Source

Local LLM Video Captioning: Private, Powerful, Open-Source

1
Comments
6 min read
How to Write Workflow Skills: Patterns and Best Practices Distilled from 7 Top Projects

How to Write Workflow Skills: Patterns and Best Practices Distilled from 7 Top Projects

6
Comments 1
6 min read
AI Hallucination Squatting: The New Agentic Attack Vector

AI Hallucination Squatting: The New Agentic Attack Vector

Comments
12 min read
Who Owns the Code Claude Wrote? The Legal Mess No One's Talking About

Who Owns the Code Claude Wrote? The Legal Mess No One's Talking About

Comments
3 min read
I Audited My Own AI Agent's Token Usage. It Was Burning €42/Month for No Reason.

I Audited My Own AI Agent's Token Usage. It Was Burning €42/Month for No Reason.

Comments
4 min read
Why Local LLMs Keep Failing at Code Generation (and How to Fix It)

Why Local LLMs Keep Failing at Code Generation (and How to Fix It)

3
Comments 1
6 min read
AIGoat - AI Security Playground to Attack and Defend LLMs. All Running Locally

AIGoat - AI Security Playground to Attack and Defend LLMs. All Running Locally

2
Comments 1
3 min read
The Accordion Pattern: Why I stopped writing one fat LLM prompt

The Accordion Pattern: Why I stopped writing one fat LLM prompt

Comments
4 min read
Seu agente de IA está desperdiçando 13.000 tokens antes de dizer "oi"

Seu agente de IA está desperdiçando 13.000 tokens antes de dizer "oi"

Comments
4 min read
Achieving Maximum Throughput on vLLM with a Single RTX 3090: A Production Guide for 7B LLMs

Achieving Maximum Throughput on vLLM with a Single RTX 3090: A Production Guide for 7B LLMs

2
Comments 1
4 min read
Structured Outputs vs Tool Calling: When Your Agent Actually Needs Which

Structured Outputs vs Tool Calling: When Your Agent Actually Needs Which

1
Comments
8 min read
Why AI Hallucinates Even When It Knows the Answer

Why AI Hallucinates Even When It Knows the Answer

1
Comments
5 min read
Stop Hardcoding Model Fallbacks: Let Production Data Pick Your Paths

Stop Hardcoding Model Fallbacks: Let Production Data Pick Your Paths

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