DEV Community

# llm

Posts

👋 Sign in for the ability to sort posts by relevant, latest, or top.
ComfyUI, Lemonade, and LocalAI: Scouting the Next Wave of Homelab AI Tools

ComfyUI, Lemonade, and LocalAI: Scouting the Next Wave of Homelab AI Tools

Comments
7 min read
Asynchronous Telemetry Blindness in AI Streaming Clients: A PoC Where Text Renders, Billing Stays at Zero

Asynchronous Telemetry Blindness in AI Streaming Clients: A PoC Where Text Renders, Billing Stays at Zero

Comments
7 min read
Your LLM-as-judge has a position bias you are not measuring

Your LLM-as-judge has a position bias you are not measuring

Comments
6 min read
Your PII redactor probably leaks tool-call arguments

Your PII redactor probably leaks tool-call arguments

Comments
3 min read
Budget enforcement for multi-agent LLM systems (without a proxy)

Budget enforcement for multi-agent LLM systems (without a proxy)

Comments
3 min read
Semantic Loop Detection: Catching Stuck AI Agents

Semantic Loop Detection: Catching Stuck AI Agents

Comments
7 min read
The paper reported jumps like 21% to 97%. My replication got +2%.

The paper reported jumps like 21% to 97%. My replication got +2%.

Comments
4 min read
Debugging Benchmark: 6 LLM Models on a Real Race Condition Bug

Debugging Benchmark: 6 LLM Models on a Real Race Condition Bug

Comments
11 min read
How we built a smart AI writing agent for blog articles

How we built a smart AI writing agent for blog articles

Comments
4 min read
Self-Hosting a Model Means Self-Hosting Its Evaluation Too

Self-Hosting a Model Means Self-Hosting Its Evaluation Too

Comments 1
5 min read
Cómo forzar output determinístico de un LLM en un agente de producción

Cómo forzar output determinístico de un LLM en un agente de producción

Comments
3 min read
When an LLM answer is wrong, the trace is where you look. Some tools make that easy.

When an LLM answer is wrong, the trace is where you look. Some tools make that easy.

Comments
5 min read
The LLM narrates. The code decides.

The LLM narrates. The code decides.

Comments 2
5 min read
Three hackathon agents, one card-free API key: what I learned building on Qwen Cloud

Three hackathon agents, one card-free API key: what I learned building on Qwen Cloud

Comments
4 min read
Stop Making Your AI Agent Smarter. Make Its Context Smaller.

Stop Making Your AI Agent Smarter. Make Its Context Smaller.

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