Blog Posts

Notes and ramblings, typically about LLMs.

LLMsinferencecost-optimizationGeminiOpenAIAWStool

Flex Inference: 50% Off LLM Calls on Gemini, OpenAI, and Bedrock

Every major AI provider now offers half-price inference if you can tolerate a few extra seconds of latency. One parameter change. Same API. Here's how it works and why.

testy.coolMay 12, 20264 min read
Flex Inference: 50% Off LLM Calls on Gemini, OpenAI, and Bedrock
geminillmfrontendautomationcachingcost-optimizationtool

A Better Way to Clone Screenshots to HTML

Using Gemini's bounding box detection to get precise measurements when converting a screenshot to code. Plus how prompt caching and flex inference make the multi-pass approach surprisingly cheap.

testy.coolMay 8, 20266 min read
A Better Way to Clone Screenshots to HTML
agentscommerceprotocolsaistandards

UCP - How to Actually Make Money With It

Universal Commerce Protocol lets AI agents buy things. Here's how developers can monetize it and what store owners need to know.

testy.coolJanuary 23, 20264 min read
UCP - How to Actually Make Money With It
claude-codesshdevops

Setting Up SSH for Claude Code

How to configure SSH so Claude Code can run commands on remote servers

testy.coolJanuary 15, 20262 min read
Setting Up SSH for Claude Code
cloudflaredeploymentseo

Fix Cloudflare Pages Redirect to Custom Domain

Your *.pages.dev URL is ranking in Google instead of your custom domain. Here's how to fix it with a proper 301 redirect.

testy.coolJanuary 7, 20263 min read
Fix Cloudflare Pages Redirect to Custom Domain
Page 1 of 2
Next