DEV Community

#codingagents

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
A semicolon in a Codex branch name leaked its GitHub token. Scope decided the damage

A semicolon in a Codex branch name leaked its GitHub token. Scope decided the damage

Comments
3 min read
Gemini 4 Argon Just Dropped — But You Can't Call It Yet: Pricing, 1M Output Tokens, and What to Do Until the API Lands

Gemini 4 Argon Just Dropped — But You Can't Call It Yet: Pricing, 1M Output Tokens, and What to Do Until the API Lands

Comments
5 min read
Claude Sonnet 5.5 Just Landed in Copilot: When to Use It, First Call, and Why List Price Lies

Claude Sonnet 5.5 Just Landed in Copilot: When to Use It, First Call, and Why List Price Lies

Comments
5 min read
O harness é o novo código: por que o desempenho do agente depende mais do ambiente de execução do que do modelo

O harness é o novo código: por que o desempenho do agente depende mais do ambiente de execução do que do modelo

Comments
3 min read
AI Made Me Write Less Code — and Think More About Engineering

AI Made Me Write Less Code — and Think More About Engineering

1
Comments 3
9 min read
The fix shipped three weeks before the bug had a name

The fix shipped three weeks before the bug had a name

Comments
4 min read
Spec-Driven Development in React Native: an MVP that lists the world's earthquakes, specified before writing code

Spec-Driven Development in React Native: an MVP that lists the world's earthquakes, specified before writing code

Comments
3 min read
Orca: the ADE for orchestrating a fleet of coding agents in parallel

Orca: the ADE for orchestrating a fleet of coding agents in parallel

Comments
3 min read
OpenClaude vs Claude Code 2026: OpenClaude Wins on Price

OpenClaude vs Claude Code 2026: OpenClaude Wins on Price

Comments
6 min read
DeepSeek V4.1-Flash Wins on Coding Agent Cost

DeepSeek V4.1-Flash Wins on Coding Agent Cost

Comments
7 min read
You can read Claude Code's whole harness now. That's what every benchmark score throws away

You can read Claude Code's whole harness now. That's what every benchmark score throws away

Comments
5 min read
DeepSeek V4 Flash 0731 and GPT-5.6 Luna: The Routing Table Just Moved

DeepSeek V4 Flash 0731 and GPT-5.6 Luna: The Routing Table Just Moved

1
Comments
13 min read
Two "Codex CLI" models on the same benchmark: the harness hides the model

Two "Codex CLI" models on the same benchmark: the harness hides the model

Comments
2 min read
Two Viral Essays, One Warning: Your AI Code Is Fine, Your Understanding Is Gone

Two Viral Essays, One Warning: Your AI Code Is Fine, Your Understanding Is Gone

2
Comments 2
6 min read
I Made Grok 4.5 My Default Coding Model for One Client Week

I Made Grok 4.5 My Default Coding Model for One Client Week

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