Riley Wu

Riley Wu

Sep 11

Hold the Loop on Disk Until the Wire Earns It

#javascript #ai #security #productivity

1

7 min read

Riley Wu

Sep 9

Weigh the Payload Before the Hop

#python #productivity #security #ai

6 min read

Riley Wu

Sep 7

Stopwatch First: Local Work or a Remote Hop

#ai #python #security #productivity

6 min read

Riley Wu

Sep 7

When Local CPU Loses to RTT

#javascript #ai #performance #node

7 min read

Riley Wu

Sep 7

Score Agent Hops Before They Leave Disk

#ai #agents #architecture #python

8 min read

Riley Wu

Sep 6

Route Prompts by Latency, Secrets, and Link

#ai #python #testing #productivity

7 min read

Riley Wu

Sep 4

Secrets Stay Local Until the Hop Is Clean

#ai #security #architecture #python

6 min read

Riley Wu

Sep 4

Score LLM-Written Tests with Mutation Testing on a Free Server

#mutationtesting #llm #pytest #python

6 min read

Riley Wu

Sep 4

SimHash Cache: Cutting 40% of Token Calls on a Free LLM Tier

#llm #python #performance #ai

2 min read

Riley Wu

Sep 4

A Free AI Code Reviewer: Hooking MonkeyCode's Server to GitHub PRs

#ai #github #tutorial #devops

4 min read

Riley Wu

Sep 4

How to Audit Bias When Free LLMs Judge Paid Models

#llmasajudge #evaluation #biasaudit #python

5 min read

Riley Wu

Sep 3

Fail Over Only After the Local Process Gasps

#python #ai #testing #devops

5 min read

Riley Wu

Sep 2

Probe Your LLM's Context: A Three-Backend Stale-Answer Test

#ai #llm #testing #architecture

4 min read

Riley Wu

Sep 1

Spend Zero Tokens on Easy Questions: A Cheap LLM Router on a Free Server

#llm #ai #architecture #webdev

4 min read

Riley Wu

Aug 31

Measure Latency, Secrets, and Offline Before Choosing a Model Endpoint

#ai #llm #localfirst #architecture

3 min read

Riley Wu

Aug 30

The Endpoint Rule: Local or Free Server?

#ai #architecture #llm #opensource

2 min read

Riley Wu

Aug 29

Local-First Inference: When Your Laptop Beats a Cloud API

#ai #llm #architecture #cloud

3 min read

Riley Wu

Aug 28

Free-Tier Model Review: A Repeatable Code Audit Pipeline That Costs Nothing

#ai #llm #devops #productivity

4 min read

Riley Wu

Aug 26

Your LLM Quota Will Run Out: A Fallback Ladder for Free-Tier Apps

#ai #python #architecture #webdev

5 min read

Riley Wu

Aug 22

Batch LLM Jobs Without Breaking the Bank: A Queue-First Architecture for Free Tiers

#python #llm #architecture #opensource

4 min read

Riley Wu

Aug 13

The Week After the Eval: A Cost-Aware Routing Harness for New Model Drops

#ai #llm #productivity #tooling

5 min read

Riley Wu

Aug 10

Hype Cycles Don't Ship My Code: How I Gate New LLMs with a Self-Written Eval Deck

#ai #testing #llm #productivity

5 min read

Riley Wu

Aug 10

Pick Your LLM With a Scoreboard, Not a Hunch: A Two-File Eval That Costs Nothing to Re-Run

#llm #testing #python #ai

6 min read

DEV Community

Badges

Writing Debut

Skills/Languages

Currently learning

Currently hacking on

Available for

Hold the Loop on Disk Until the Wire Earns It

Weigh the Payload Before the Hop

Stopwatch First: Local Work or a Remote Hop

When Local CPU Loses to RTT

Score Agent Hops Before They Leave Disk

Route Prompts by Latency, Secrets, and Link

Secrets Stay Local Until the Hop Is Clean

Score LLM-Written Tests with Mutation Testing on a Free Server

SimHash Cache: Cutting 40% of Token Calls on a Free LLM Tier

A Free AI Code Reviewer: Hooking MonkeyCode's Server to GitHub PRs

How to Audit Bias When Free LLMs Judge Paid Models

Fail Over Only After the Local Process Gasps

Probe Your LLM's Context: A Three-Backend Stale-Answer Test

Spend Zero Tokens on Easy Questions: A Cheap LLM Router on a Free Server

Measure Latency, Secrets, and Offline Before Choosing a Model Endpoint

The Endpoint Rule: Local or Free Server?

Local-First Inference: When Your Laptop Beats a Cloud API

Free-Tier Model Review: A Repeatable Code Audit Pipeline That Costs Nothing

Your LLM Quota Will Run Out: A Fallback Ladder for Free-Tier Apps

Batch LLM Jobs Without Breaking the Bank: A Queue-First Architecture for Free Tiers

The Week After the Eval: A Cost-Aware Routing Harness for New Model Drops

Hype Cycles Don't Ship My Code: How I Gate New LLMs with a Self-Written Eval Deck

Pick Your LLM With a Scoreboard, Not a Hunch: A Two-File Eval That Costs Nothing to Re-Run