DEV Community

#llm

Posts

👋 Sign in for the ability to sort posts by relevant, latest, or top.
Why Your Agent Loops Need Independent Verification

Why Your Agent Loops Need Independent Verification

2
Comments 3
7 min read
How vLLM Actually Manages KV Cache (vs the Toy Version I Built)

How vLLM Actually Manages KV Cache (vs the Toy Version I Built)

3
Comments 4
4 min read
Don't trust "Done." — forcing AI agents to re-fetch reality before they report completion

Don't trust "Done." — forcing AI agents to re-fetch reality before they report completion

1
Comments 10
7 min read
14 Core Features you need for your LLM calls which VernLLM covers

14 Core Features you need for your LLM calls which VernLLM covers

1
Comments
4 min read
Claude Opus 5: beats Fable 5 at half the price — and 'awakens' in its own system card

Claude Opus 5: beats Fable 5 at half the price — and 'awakens' in its own system card

Comments
4 min read
Did the Model Upgrade Break Your AI Agent?

How silent behavioral shifts break passing tests

Did the Model Upgrade Break Your AI Agent?

16
Comments 18
3 min read
بارامتر الجهد لكلود أوبوس 5: مقايضة التكلفة مقابل القدرة

بارامتر الجهد لكلود أوبوس 5: مقايضة التكلفة مقابل القدرة

Comments
3 min read
Parâmetro de Esforço do Claude Opus 5: Trocando Custo por Capacidade

Parâmetro de Esforço do Claude Opus 5: Trocando Custo por Capacidade

Comments
10 min read
Making a launch video for Claude Opus 5

Making a launch video for Claude Opus 5

Comments
7 min read
Why Your Multi-Agent AI System Keeps Getting Stuck in Infinite Loops (And How We Fixed It)

Why Your Multi-Agent AI System Keeps Getting Stuck in Infinite Loops (And How We Fixed It)

Comments 1
3 min read
Your Prompt Templates Are Tool Calls: How AskUserQuestion's 4-Option Cap Bit Me Three Times

Your Prompt Templates Are Tool Calls: How AskUserQuestion's 4-Option Cap Bit Me Three Times

5
Comments 1
4 min read
Qwen2 is here. It’s time to re-evaluate your default model choices.

Qwen2 is here. It’s time to re-evaluate your default model choices.

Comments
3 min read
The Watermelon Effect: How My AI Scored 94% in Testing But Only 22.2% in Real Use

The Watermelon Effect: How My AI Scored 94% in Testing But Only 22.2% in Real Use

Comments
6 min read
JSON Schema Doesn't Prevent AI Hallucinations (And That's Okay)

JSON Schema Doesn't Prevent AI Hallucinations (And That's Okay)

Comments
3 min read
Tinkuy 0.1.0 — Donde los ríos se encuentran

Tinkuy 0.1.0 — Donde los ríos se encuentran

7
Comments 1
2 min read
👋 Sign in for the ability to sort posts by relevant, latest, or top.