DEV Community

#llm

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
Deep Dive into Open Agent SDK (Part 6): Multi-LLM Providers and Runtime Controls

Deep Dive into Open Agent SDK (Part 6): Multi-LLM Providers and Runtime Controls

Comments
13 min read
ModelChain: Measurable LLM Router with Adaptive Model Selection, Real-Time Scoring, Budget Guards and Failover for Node.js, Edge and Browser

ModelChain: Measurable LLM Router with Adaptive Model Selection, Real-Time Scoring, Budget Guards and Failover for Node.js, Edge and Browser

1
Comments 1
3 min read
Skills for eval-driven agent optimization

Skills for eval-driven agent optimization

1
Comments
1 min read
62.2% on Aider Polyglot from a MacBook Pro. Then the other model we tried scored 4%. Here's what actually happened, with a working cost loop attached.

62.2% on Aider Polyglot from a MacBook Pro. Then the other model we tried scored 4%. Here's what actually happened, with a working cost loop attached.

Comments
16 min read
What If You Compressed Your Prompts Into Chinese Emoji? (A Token-Saving Thought Experiment)

What If You Compressed Your Prompts Into Chinese Emoji? (A Token-Saving Thought Experiment)

Comments
3 min read
Engineering Agent Memory

Working, semantic, and episodic memory layers

Engineering Agent Memory

31
Comments 116
10 min read
GEO / AI Search Thread

GEO / AI Search Thread

Comments
5 min read
Stop Caching the Whole LLM Response. Cache the Embedding.

Stop Caching the Whole LLM Response. Cache the Embedding.

Comments
8 min read
Hybrid Search Is the Phrase You'll Hear at Every RAG Talk in 2026

Hybrid Search Is the Phrase You'll Hear at Every RAG Talk in 2026

Comments
7 min read
Building a harness that makes a small LLM reliable

Building a harness that makes a small LLM reliable

Comments 1
11 min read
The 3 Alerts Every LLM Team Should Have Set Up by Tomorrow

The 3 Alerts Every LLM Team Should Have Set Up by Tomorrow

Comments
7 min read
The JSON-Mode Prompt Pattern That Survives Claude Version Bumps

The JSON-Mode Prompt Pattern That Survives Claude Version Bumps

Comments
7 min read
Your RAG Eval Set Is Probably Wrong. The Test That Catches It.

Your RAG Eval Set Is Probably Wrong. The Test That Catches It.

Comments
7 min read
Hugging Face Pulled Dozens of Backdoored Models. Here's the Pattern.

Hugging Face Pulled Dozens of Backdoored Models. Here's the Pattern.

Comments
7 min read
The 100-Line LLM Cache That Pays For Itself in a Week

The 100-Line LLM Cache That Pays For Itself in a Week

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