DEV Community

#llm

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
LLM Observability Tools Compared: The 2026 Landscape

LLM Observability Tools Compared: The 2026 Landscape

Comments
5 min read
"A Survey of LLM-based Deep Search Agents" (2026)

"A Survey of LLM-based Deep Search Agents" (2026)

Comments 1
2 min read
I built an AI chat app because I was tired of AI sounding like a corporate memo

I built an AI chat app because I was tired of AI sounding like a corporate memo

1
Comments 1
2 min read
Built an open-source memory layer for local LLMs — single-shot calls, auto-extracted constraints, no context degradation

Built an open-source memory layer for local LLMs — single-shot calls, auto-extracted constraints, no context degradation

Comments
1 min read
MAI-Thinking-1: Microsoft's New Reasoning Model and What It Means for Developers

MAI-Thinking-1: Microsoft's New Reasoning Model and What It Means for Developers

7
Comments 1
6 min read
Building WeaveLLM: Why .NET Deserves a Better then LangChain

Building WeaveLLM: Why .NET Deserves a Better then LangChain

Comments
9 min read
My agent swarm had a productive night. My pipeline lied about it.

My agent swarm had a productive night. My pipeline lied about it.

1
Comments 1
5 min read
How LLMs Actually Work: A Developer's Mental Model

How LLMs Actually Work: A Developer's Mental Model

1
Comments
6 min read
What Happens When You Evaluate a B2B Sales Agent on Tasks It Was Never Designed For

What Happens When You Evaluate a B2B Sales Agent on Tasks It Was Never Designed For

Comments
5 min read
Vibe Coding vs Prompt Engineering vs Context Engineering — What's the Difference?

Vibe Coding vs Prompt Engineering vs Context Engineering — What's the Difference?

Comments 1
4 min read
The Essence

The Essence

Comments
4 min read
I tested 4 free 70B-class LLM endpoints for real production work — here's what each is actually good at

I tested 4 free 70B-class LLM endpoints for real production work — here's what each is actually good at

Comments
5 min read
Hybrid LLM Routing: Ollama + Claude API Without Quality Degradation

Hybrid LLM Routing: Ollama + Claude API Without Quality Degradation

Comments
4 min read
I tested 4 local models as memory classifiers for OpenClaw — and thinking models are a trap

I tested 4 local models as memory classifiers for OpenClaw — and thinking models are a trap

Comments
5 min read
Gemma 4 12B: Google's encoder-free multimodal AI now runs on a laptop

Gemma 4 12B: Google's encoder-free multimodal AI now runs on a laptop

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