DEV Community

Artificial Intelligence

Artificial intelligence leverages computers and machines to mimic the problem-solving and decision-making capabilities found in humans and in nature.

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
Agents of Chaos: a field study of 16 agent failures (and refusals)

Agents of Chaos: a field study of 16 agent failures (and refusals)

Comments
4 min read
Similarity Search for Failure Diagnosis

Similarity Search for Failure Diagnosis

Comments
4 min read
I built a local-first movie recommender with Corrective-RAG (cited explanations, hybrid retrieval, runs entirely on Ollama)

I built a local-first movie recommender with Corrective-RAG (cited explanations, hybrid retrieval, runs entirely on Ollama)

Comments
1 min read
How I Slashed My AI API Bill by 95% — A Practical Guide for 2026

How I Slashed My AI API Bill by 95% — A Practical Guide for 2026

Comments 2
4 min read
Three Failures My AI Memory System Tested — And the Flaw It Revealed in Itself

Three Failures My AI Memory System Tested — And the Flaw It Revealed in Itself

Comments
6 min read
Vibe Coding Problems: 7 Visual Bugs AI Code Generators Always Ship

Vibe Coding Problems: 7 Visual Bugs AI Code Generators Always Ship

1
Comments
3 min read
Gemini Omni makes video generation feel more like editing

Gemini Omni makes video generation feel more like editing

6
Comments
4 min read
Months of self-testing: Citations shine, other features remain unproven.

Months of self-testing: Citations shine, other features remain unproven.

Comments 1
3 min read
I Added a 4th Agent That Audits My Other Agents. It Caught My Strategist Procrastinating for 3 Weeks.

I Added a 4th Agent That Audits My Other Agents. It Caught My Strategist Procrastinating for 3 Weeks.

Comments
9 min read
How a 400-Engineer SaaS Company Cut PR-to-Production from 4.2 Days to 6.4 Hours with Claude Code Multi-Agent DevOps

How a 400-Engineer SaaS Company Cut PR-to-Production from 4.2 Days to 6.4 Hours with Claude Code Multi-Agent DevOps

Comments
6 min read
Three Error Recovery Patterns for LLM Agent Tool Failures

Three Error Recovery Patterns for LLM Agent Tool Failures

Comments
5 min read
My RAG system slowly got worse for three months and nobody noticed.

My RAG system slowly got worse for three months and nobody noticed.

Comments
4 min read
cachebench: stop finding out about prompt-cache regressions from the invoice

cachebench: stop finding out about prompt-cache regressions from the invoice

Comments
4 min read
Four Patterns for Multi-Agent Python Systems That Actually Work

Four Patterns for Multi-Agent Python Systems That Actually Work

Comments
5 min read
How to Test LLM Agents Without Calling the Real API

How to Test LLM Agents Without Calling the Real API

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