Nate Voss

Indie dev building tools for AI workflows. writing about what I learn.

Joined on Mar 23, 2026

Nate Voss

May 6

I wrote a rule after Claude got "is X built?" wrong 4 times. Looking for failure modes.

#ai #llm #programming #claude

4 min read

Want to connect with Nate Voss?

Create an account to connect with Nate Voss. You can also sign in below to proceed if you already have an account.

Create Account

Already have an account? Sign in

Nate Voss

May 6

Pre-Build Existence Audit Rule : looking for the failure modes I'm still missing

#ai #llm #programming #claude

4 min read

Nate Voss

May 6

4 rules I added to my CLAUDE.md after a week of weird CLI bugs

#claudecode #ai #productivity #devtools

3 min read

Nate Voss

May 4

Model Routing: 3 Things I Learned Sending Tasks to the Cheapest Model That Actually Works

#ai #tutorial #javascript #beginners

4 min read

Nate Voss

Apr 27

3 Things I Learned Auditing My LLM App's Token Spend (And Why Your Benchmarks Are Lying)

#ai #tutorial #javascript #beginners

3 min read

Nate Voss

Apr 27

3 Things I Learned Auditing My LLM App's Token Spend (And Why Your Benchmarks Are Lying)

#ai #tutorial #javascript #beginners

3 min read

Nate Voss

Apr 27

3 Things I Learned Auditing My LLM App's Token Spend (And Why Your Benchmarks Are Lying)

#ai #tutorial #javascript #beginners

3 min read

Nate Voss

Apr 23

How I Accidentally Spent $800/Month on LLM Tokens I Didn't Need (And How to Fix It)

#ai #tutorial #javascript #beginners

4 min read

Nate Voss

Apr 21

3 Things I Learned Benchmarking Claude, GPT-4o, and Gemini on Real Dev Work

#ai #tutorial #javascript #optimization

4 min read

Nate Voss

Apr 21

3 Things I Learned Benchmarking Claude, GPT-4o, and Gemini on Real Dev Work

#ai #tutorial #javascript #optimization

4 min read

Nate Voss

Apr 17

I Tested Claude Haiku, GPT-4o Mini, and Gemini Flash on Real Tasks. Here's What Actually Happened.

#ai #tutorial #javascript #optimization

3 min read

DEV Community

Nate Voss

Badges

Writing Debut

I wrote a rule after Claude got "is X built?" wrong 4 times. Looking for failure modes.

Want to connect with Nate Voss?

Pre-Build Existence Audit Rule : looking for the failure modes I'm still missing

4 rules I added to my CLAUDE.md after a week of weird CLI bugs

Model Routing: 3 Things I Learned Sending Tasks to the Cheapest Model That Actually Works

3 Things I Learned Auditing My LLM App's Token Spend (And Why Your Benchmarks Are Lying)

3 Things I Learned Auditing My LLM App's Token Spend (And Why Your Benchmarks Are Lying)

3 Things I Learned Auditing My LLM App's Token Spend (And Why Your Benchmarks Are Lying)

How I Accidentally Spent $800/Month on LLM Tokens I Didn't Need (And How to Fix It)

3 Things I Learned Benchmarking Claude, GPT-4o, and Gemini on Real Dev Work

3 Things I Learned Benchmarking Claude, GPT-4o, and Gemini on Real Dev Work

I Tested Claude Haiku, GPT-4o Mini, and Gemini Flash on Real Tasks. Here's What Actually Happened.