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.
Atlarix vs opencode on Terminal-Bench 2.0 — same model, only the harness changes (k=1, receipts included)

Atlarix vs opencode on Terminal-Bench 2.0 — same model, only the harness changes (k=1, receipts included)

Comments
3 min read
A benchmark is a claim until someone can replay it

A benchmark is a claim until someone can replay it

Comments
2 min read
Coordinate-space diffusion improves video consistency

Coordinate-space diffusion improves video consistency

Comments
2 min read
MCP-Ready MVPs: Should Startups Build Tool-Connected AI Products From Day One?

MCP-Ready MVPs: Should Startups Build Tool-Connected AI Products From Day One?

8
Comments 2
9 min read
: I Built an AI That Scans Repos, Screens Candidates, and Agents Inside VS Code — As a 2nd Year CS Student

: I Built an AI That Scans Repos, Screens Candidates, and Agents Inside VS Code — As a 2nd Year CS Student

Comments
5 min read
The Bridge Looked Fine Too

The Bridge Looked Fine Too

Comments
7 min read
Get 15 RPM / 500 RPD for Free! Google Gemini 3.1 Flash-Lite API Guide & Translation Setup

Get 15 RPM / 500 RPD for Free! Google Gemini 3.1 Flash-Lite API Guide & Translation Setup

Comments
1 min read
Making JetBrains AI Assistant work with Gemini: v0.0.2 is out

Making JetBrains AI Assistant work with Gemini: v0.0.2 is out

Comments
2 min read
Building Quudos: a casting platform on Amazon Aurora + Vercel

Building Quudos: a casting platform on Amazon Aurora + Vercel

Comments
3 min read
RAG for codebases is hard. Trusting the answer is harder.

RAG for codebases is hard. Trusting the answer is harder.

Comments 1
4 min read
hermes-memory-installer: Memory Sidecar v3.5.1

hermes-memory-installer: Memory Sidecar v3.5.1

Comments
2 min read
Testing Qwen-AgentWorld-35B-A3B: A New Benchmark for Agentic Reasoning?

Testing Qwen-AgentWorld-35B-A3B: A New Benchmark for Agentic Reasoning?

Comments
2 min read
The "4 layers to stop Claude lying" setup is a duct-tape stack. Here's what a single hook does instead.

The "4 layers to stop Claude lying" setup is a duct-tape stack. Here's what a single hook does instead.

Comments 6
6 min read
Why Playwright MCP Cost Us 5 More Tokens Than We Expected

Why Playwright MCP Cost Us 5 More Tokens Than We Expected

Comments
3 min read
What AutoGPT ships in 2026: a low-code platform for continuous AI agents

What AutoGPT ships in 2026: a low-code platform for continuous AI agents

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