DEV Community

#llm

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
The Hell of AI Agent Development

The Hell of AI Agent Development

5
Comments 2
8 min read
Taming Opus 4.5's Efficiency: Using TodoWrite to Keep Claude Code on Track

Taming Opus 4.5's Efficiency: Using TodoWrite to Keep Claude Code on Track

Comments
2 min read
Local LLM Hosting: Complete 2025 Guide - Ollama, vLLM, LocalAI, Jan, LM Studio & More

Local LLM Hosting: Complete 2025 Guide - Ollama, vLLM, LocalAI, Jan, LM Studio & More

1
Comments
19 min read
A Financial MCP server with multi-provider orchestration (Open Source)

A Financial MCP server with multi-provider orchestration (Open Source)

Comments
1 min read
Supercharge Your Fish Shell: Stop Googling, Start Commanding with AI

Supercharge Your Fish Shell: Stop Googling, Start Commanding with AI

Comments
3 min read
Demystifying Agentic Test Automation for QA Teams

Demystifying Agentic Test Automation for QA Teams

2
Comments
5 min read
“I've failed 17 consecutive times with the exact same error”

“I've failed 17 consecutive times with the exact same error”

1
Comments
5 min read
We built an LLM gateway 50x faster than LiteLLM (and it's open source)

We built an LLM gateway 50x faster than LiteLLM (and it's open source)

1
Comments
3 min read
LLM Gateway Comparison: Bifrost vs LiteLLM (2025)

LLM Gateway Comparison: Bifrost vs LiteLLM (2025)

3
Comments
3 min read
CLaRa: Fixing RAG’s Broken Retrieval–Generation Pipeline With Shared-Space Learning

CLaRa: Fixing RAG’s Broken Retrieval–Generation Pipeline With Shared-Space Learning

3
Comments
3 min read
AWSChallenge - Week 1

AWSChallenge - Week 1

3
Comments
4 min read
AI Automation: How to Build LLM Apps, AI Agents and Automated Workflows

AI Automation: How to Build LLM Apps, AI Agents and Automated Workflows

1
Comments
3 min read
Everyone says to have better context management. I'll show you how I built it.

Everyone says to have better context management. I'll show you how I built it.

Comments
6 min read
LLMs as Unreliable Narrators: Dealing with UUID Hallucination

LLMs as Unreliable Narrators: Dealing with UUID Hallucination

8
Comments
5 min read
The Science of Prompt Evaluation: From BLEU & ROUGE to Real Human Feedback

The Science of Prompt Evaluation: From BLEU & ROUGE to Real Human Feedback

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