DEV Community

Casey Li profile picture

Casey Li

Frontend developer crafting beautiful user experiences.

Location Sydney, Australia Joined Joined on 
Token Buckets Do Not Belong on Free Inference

Token Buckets Do Not Belong on Free Inference

1
Comments 1
7 min read
The Lease Loop Is Not a Chat Completion

The Lease Loop Is Not a Chat Completion

1
Comments
7 min read
Privilege Grants Do Not Belong on Free Inference

Privilege Grants Do Not Belong on Free Inference

1
Comments
9 min read
Live Schema Changes Do Not Belong on Free Inference

Live Schema Changes Do Not Belong on Free Inference

Comments
5 min read
Canary Verdicts Do Not Belong on Free Inference

Canary Verdicts Do Not Belong on Free Inference

1
Comments
8 min read
Red Flags Before Routing a Workload Through a Free Tier

Red Flags Before Routing a Workload Through a Free Tier

Comments
6 min read
When Free Inference Should Not Own the Retry Loop

When Free Inference Should Not Own the Retry Loop

Comments 2
7 min read
When Free Inference Should Not Back an MCP Tool

When Free Inference Should Not Back an MCP Tool

1
Comments 3
6 min read
Free Inference Should Not Gate a Merge

Free Inference Should Not Gate a Merge

Comments 2
7 min read
Free Inference Should Not Grant Tool Access

Free Inference Should Not Grant Tool Access

Comments
7 min read
Free Inference Stops at the Persistence Boundary

Free Inference Stops at the Persistence Boundary

Comments
7 min read
When Not to Host an Agent on Free Inference

When Not to Host an Agent on Free Inference

1
Comments
6 min read
When Free Inference Should Not Own the Contract

When Free Inference Should Not Own the Contract

1
Comments
6 min read
Stop Conditions for Free Inference in Agent Loops

Stop Conditions for Free Inference in Agent Loops

Comments
7 min read
Free Model Night Incident Drafts on a Free Server

Free Model Night Incident Drafts on a Free Server

Comments
6 min read
Keep Free Inference Off the Merge Path

Keep Free Inference Off the Merge Path

Comments
5 min read
Free Tokens Burn Fast: A Field Guide to MonkeyCode's Generosity

Free Tokens Burn Fast: A Field Guide to MonkeyCode's Generosity

Comments
4 min read
Probing Free LLM Servers for Cross-Session Memory Leaks

Probing Free LLM Servers for Cross-Session Memory Leaks

Comments 1
3 min read
Free Model Meets Free Server: Designing a Repeatable Reliability Experiment

Free Model Meets Free Server: Designing a Repeatable Reliability Experiment

Comments
5 min read
Free Models, Free Server: A 30-Minute Quota Probe Before You Trust Either

Free Models, Free Server: A 30-Minute Quota Probe Before You Trust Either

Comments
6 min read
When Not to Use a Free Model Server: Red Flags, Alternatives, and Exit Criteria

When Not to Use a Free Model Server: Red Flags, Alternatives, and Exit Criteria

Comments
6 min read
Free LLM Servers: Red Flags, Safer Alternatives, Exit Criteria

Free LLM Servers: Red Flags, Safer Alternatives, Exit Criteria

Comments
4 min read
When Free Is the Wrong Price: A Field Guide for LLM Free Tiers

When Free Is the Wrong Price: A Field Guide for LLM Free Tiers

Comments
5 min read
Free-Tier CI Triage: One Small Bot, End to End

Free-Tier CI Triage: One Small Bot, End to End

Comments
5 min read
Zero-Budget Release Notes: A Case Study in Free-Tier LLM Automation

Zero-Budget Release Notes: A Case Study in Free-Tier LLM Automation

1
Comments
6 min read
Free Models as Test Doubles: A Dev/Prod Split That Saves Real Money

Free Models as Test Doubles: A Dev/Prod Split That Saves Real Money

Comments
4 min read
I Stopped Reading AI Benchmarks and Started Testing Cheap Models for Free

I Stopped Reading AI Benchmarks and Started Testing Cheap Models for Free

Comments
3 min read
Before You Adopt MiniMax H3, Run a Twenty-Minute Model Audit

Before You Adopt MiniMax H3, Run a Twenty-Minute Model Audit

Comments
3 min read
Before You Give a Coding Agent Shell Access: A Boundary Test Harness You Can Run in an Afternoon

Before You Give a Coding Agent Shell Access: A Boundary Test Harness You Can Run in an Afternoon

Comments
6 min read
loading...