DEV Community

Taylor Wang profile picture

Taylor Wang

Full-stack developer passionate about open source and clean code.

Location Berlin, Germany Joined Joined on 
Bind OSS Patches to a Replay Command and File Allowlist

Bind OSS Patches to a Replay Command and File Allowlist

Comments
7 min read
Keep OSS Reviews Inside a Four-File Packet

Keep OSS Reviews Inside a Four-File Packet

Comments
7 min read
Gate OSS Patches With a Four-Check Review Packet

Gate OSS Patches With a Four-Check Review Packet

Comments
5 min read
Score Incoming OSS PRs Against the Issue Contract

Score Incoming OSS PRs Against the Issue Contract

Comments
6 min read
Free AI Tiers Fail Differently. Run a Budget Burn-Down Before You Commit.

Free AI Tiers Fail Differently. Run a Budget Burn-Down Before You Commit.

Comments
4 min read
3-Agent Pipeline: Better Code from Free-Tier Models

3-Agent Pipeline: Better Code from Free-Tier Models

Comments
6 min read
Reproduce First, Then Patch: An OSS Fix Loop

Reproduce First, Then Patch: An OSS Fix Loop

Comments
7 min read
Iterating on AI Code-Review Prompts Without Spending a Token

Iterating on AI Code-Review Prompts Without Spending a Token

Comments
5 min read
Golden Patches: Test Your AI Reviewer Before It Tests Others

Golden Patches: Test Your AI Reviewer Before It Tests Others

Comments
4 min read
CI Is Green. The Patch Can Still Lie.

CI Is Green. The Patch Can Still Lie.

Comments
3 min read
Free-Model PR Triage: A Working Script for Maintainers

Free-Model PR Triage: A Working Script for Maintainers

Comments
3 min read
First-Run MonkeyCode: Free Server, Free Tokens, One Merge Gate

First-Run MonkeyCode: Free Server, Free Tokens, One Merge Gate

Comments
4 min read
A PR Review Gate That Fails Closed: Free Models in CI

A PR Review Gate That Fails Closed: Free Models in CI

Comments
6 min read
Reproduce, Patch, Test: A Free-Model Review Loop for Open Source PRs

Reproduce, Patch, Test: A Free-Model Review Loop for Open Source PRs

Comments
4 min read
Free Model + Free Server: A Reproducible 12-Task Eval for AI Coding Agents

Free Model + Free Server: A Reproducible 12-Task Eval for AI Coding Agents

Comments
4 min read
When a Free Model Meets a Real Codebase: A Refactor's Failure Map

When a Free Model Meets a Real Codebase: A Refactor's Failure Map

Comments
4 min read
A $0 Model Evaluation Loop Before Your Next Model Swap

A $0 Model Evaluation Loop Before Your Next Model Swap

Comments
4 min read
Let the Test Suite Decide Which Model Answers: A Verification-Gated Model Ladder

Let the Test Suite Decide Which Model Answers: A Verification-Gated Model Ladder

Comments
6 min read
Before You Switch to the Hottest Open-Weight Model, Run This 30-Minute Eval Harness

Before You Switch to the Hottest Open-Weight Model, Run This 30-Minute Eval Harness

Comments
4 min read
A Disposable Sandbox Pattern for Testing AI Coding Agents Safely

A Disposable Sandbox Pattern for Testing AI Coding Agents Safely

Comments
4 min read
loading...