DEV Community

# llm

Posts

👋 Sign in for the ability to sort posts by relevant, latest, or top.
80% of RAG Failures Start Here (And It's Not the LLM)

80% of RAG Failures Start Here (And It's Not the LLM)

4
Comments
2 min read
AI Agents for Enterprise Data Analytics: From Chat Interfaces to Reliable Execution

AI Agents for Enterprise Data Analytics: From Chat Interfaces to Reliable Execution

5
Comments
3 min read
Running Just One LLM on 8GB VRAM Is a Waste

Running Just One LLM on 8GB VRAM Is a Waste

Comments
8 min read
Solving the LLM Black Box Problem with Structured Reasoning

Solving the LLM Black Box Problem with Structured Reasoning

4
Comments 4
4 min read
Local LLMs Vs Cloud AI APIs: Which One Should Developers Use For Real Projects?

Local LLMs Vs Cloud AI APIs: Which One Should Developers Use For Real Projects?

8
Comments 1
5 min read
I built an AI Gateway with no technical background. Here's where I'm stuck.

I built an AI Gateway with no technical background. Here's where I'm stuck.

Comments
1 min read
ツール呼び出しでも大きいモデルは勝てなかった

ツール呼び出しでも大きいモデルは勝てなかった

Comments
4 min read
I benchmarked GPT-4o, Claude 3.5, and Gemini 1.5 for security — the results

I benchmarked GPT-4o, Claude 3.5, and Gemini 1.5 for security — the results

Comments
2 min read
How to verify AI-discovered vulnerabilities aren't just training data echoes

How to verify AI-discovered vulnerabilities aren't just training data echoes

2
Comments
5 min read
LLMs for Product Descriptions at Scale: How D2C Brands Can Auto-Generate SEO Copy Without Sounding Like a Bot

LLMs for Product Descriptions at Scale: How D2C Brands Can Auto-Generate SEO Copy Without Sounding Like a Bot

Comments
7 min read
Building Your Own "Google Maps for Codebases": A Guide to Semantic Code Search with LLMs

Building Your Own "Google Maps for Codebases": A Guide to Semantic Code Search with LLMs

Comments
5 min read
The $500 GPU That Outperforms Claude Sonnet on Coding Benchmarks

The $500 GPU That Outperforms Claude Sonnet on Coding Benchmarks

Comments
4 min read
Agentic AI: Why 2026 Is The Year Everything Changes

Agentic AI: Why 2026 Is The Year Everything Changes

1
Comments 1
2 min read
We Hit 99.1% on the LOCOMO Benchmark. Here's How.

We Hit 99.1% on the LOCOMO Benchmark. Here's How.

Comments
2 min read
I kept rewriting the same regex passes against LLM output. So I made a library.

I kept rewriting the same regex passes against LLM output. So I made a library.

1
Comments 4
5 min read
👋 Sign in for the ability to sort posts by relevant, latest, or top.