DEV Community

Finley Zhu profile picture

Finley Zhu

DevOps enthusiast automating all the things.

Location Beijing, China Joined Joined on 
Workshop: Reject Incomplete Agent Plans Before Side Effects in 80 Minutes

Workshop: Reject Incomplete Agent Plans Before Side Effects in 80 Minutes

Comments
9 min read
How I Audit Error Messages With Free AI Compute

How I Audit Error Messages With Free AI Compute

Comments
6 min read
Artificial Scarcity: Why I Cap My AI Token Usage Below the Free Limit

Artificial Scarcity: Why I Cap My AI Token Usage Below the Free Limit

Comments
4 min read
Designing for Shared LLM Infrastructure: Timeouts, Retries, and Circuit Breakers That Actually Work

Designing for Shared LLM Infrastructure: Timeouts, Retries, and Circuit Breakers That Actually Work

Comments
4 min read
Workshop: Fail Closed on Hallucinated Tool Arguments in 65 Minutes

Workshop: Fail Closed on Hallucinated Tool Arguments in 65 Minutes

Comments
7 min read
Workshop: Gate Retrieved Context With a Cheap Scoring Pass in 70 Minutes

Workshop: Gate Retrieved Context With a Cheap Scoring Pass in 70 Minutes

1
Comments
8 min read
Workshop: Find the Technical Debt Your AI Reviewer Left Behind in 75 Minutes

Workshop: Find the Technical Debt Your AI Reviewer Left Behind in 75 Minutes

Comments
5 min read
Zero-Cost Prompt Routing: Stop Sending Every Task to the Most Expensive Model

Zero-Cost Prompt Routing: Stop Sending Every Task to the Most Expensive Model

Comments
5 min read
Your LLM Returns Invalid JSON? Repair It with Free Models on a Free Server

Your LLM Returns Invalid JSON? Repair It with Free Models on a Free Server

Comments
4 min read
Workshop: Test Your AI Reviewer With a 15-Case Golden Set in 60 Minutes

Workshop: Test Your AI Reviewer With a 15-Case Golden Set in 60 Minutes

Comments
5 min read
Workshop: Benchmark a New Open-Weight Model in 60 Minutes on Free Tokens and a Free Server

Workshop: Benchmark a New Open-Weight Model in 60 Minutes on Free Tokens and a Free Server

Comments
6 min read
Workshop: Build a Metered LLM App in 90 Minutes on Free Infrastructure

Workshop: Build a Metered LLM App in 90 Minutes on Free Infrastructure

Comments
5 min read
The Slow Lane: Latency Engineering When Your AI Endpoint Is Free

The Slow Lane: Latency Engineering When Your AI Endpoint Is Free

1
Comments
4 min read
Token Forensics: Metering AI Spend Before You Optimize Anything

Token Forensics: Metering AI Spend Before You Optimize Anything

Comments 1
6 min read
Free AI Tokens Are a Trap: An Opinionated Cost Gate for Model Experiments

Free AI Tokens Are a Trap: An Opinionated Cost Gate for Model Experiments

Comments
5 min read
The 10-Minute Gate: Testing a Cheap New Model Without Rebuilding Your Stack

The 10-Minute Gate: Testing a Cheap New Model Without Rebuilding Your Stack

Comments
3 min read
New Open-Weight Model Drops Every Week. Here's a Reproducible Way to Decide If It Belongs in Your Workflow

New Open-Weight Model Drops Every Week. Here's a Reproducible Way to Decide If It Belongs in Your Workflow

Comments
5 min read
Your AI Reviewer Needs a Reviewer: A Free Pipeline for Stress-Testing Suggested Diffs

Your AI Reviewer Needs a Reviewer: A Free Pipeline for Stress-Testing Suggested Diffs

Comments
5 min read
loading...