DEV Community

#llm

Posts

👋 Sign in for the ability to sort posts by relevant, latest, or top.
Four Ways to Build Solon AI Tools: Annotations, FunctionToolDesc, returnDirect, and toolContext

Four Ways to Build Solon AI Tools: Annotations, FunctionToolDesc, returnDirect, and toolContext

Comments
6 min read
Running Local LLMs in Java: Introducing jllm – A Minimalist Ollama Alternative

Running Local LLMs in Java: Introducing jllm – A Minimalist Ollama Alternative

Comments
3 min read
Your cheap LLM relay might be swapping the model. Here's how to catch it.

Your cheap LLM relay might be swapping the model. Here's how to catch it.

Comments
7 min read
Part 6: Observability for AI Agents: Tracing, Metrics, and Drift

Part 6: Observability for AI Agents: Tracing, Metrics, and Drift

Comments 2
4 min read
Alibaba เปิด Qwen3.8-Max Open Source — นี่แปลว่าอะไรสำหรับอนาคตของ Open-Weight AI

Alibaba เปิด Qwen3.8-Max Open Source — นี่แปลว่าอะไรสำหรับอนาคตของ Open-Weight AI

Comments
3 min read
I tested whether agents leak secrets without being asked — and whether my scanner catches it when they do

I tested whether agents leak secrets without being asked — and whether my scanner catches it when they do

Comments 8
8 min read
Don't Give the Model SQL

Real-world health data traps beat prompts

Don't Give the Model SQL

14
Comments 8
11 min read
André Dias Moreira Prol: Securely Connecting AI to Internal Docs With RAG

André Dias Moreira Prol: Securely Connecting AI to Internal Docs With RAG

1
Comments
3 min read
AI is not for Indie Dev

AI is not for Indie Dev

Comments
2 min read
Build an MCP Nutrition Server

Build an MCP Nutrition Server

5
Comments
4 min read
How LLMLingua compresses prompts: perplexity, deletion, and trust

How LLMLingua compresses prompts: perplexity, deletion, and trust

Comments
4 min read
One key for CrewAI, AutoGen, LlamaIndex and 8 more: the base_url trick for Python agents

One key for CrewAI, AutoGen, LlamaIndex and 8 more: the base_url trick for Python agents

Comments
5 min read
Your cheap LLM relay might be swapping the model. Here's how to catch it.

Your cheap LLM relay might be swapping the model. Here's how to catch it.

Comments
7 min read
Same Model, Two Speeds: A Friendly Tour of LLM Inference Engines

Same Model, Two Speeds: A Friendly Tour of LLM Inference Engines

19
Comments 1
7 min read
A benchmark is only as good as the model you use to grade it

Costs twenty-one cents and exposes grading bias

A benchmark is only as good as the model you use to grade it

2
Comments 4
9 min read
👋 Sign in for the ability to sort posts by relevant, latest, or top.