Blog

Guides, tutorials, and insights on AI coding tools and API providers.

· 11 min read

OpenAI Caching: How We Cut API Costs by 67% (After a $4,200 Mistake)

Last Tuesday at 3 AM, my PagerDuty went off. Actually, wait—it was Wednesday. I remember because I'd just finished prepping for our Wednesday standup and was ab

Read more →
· 7 min read

We Ditched GitHub Copilot for Cursor and Saved €8,400/Year (But That's Not Even the Best Part)

TL;DR: Our 12-person startup migrated from GitHub Copilot to Cursor. The money we saved was nice—€8,400/year is real cash. But the actual win? Our workflow got

Read more →
· 12 min read

The AI API Cost Black Hole: How Our 3-Person Startup Slashed Our OpenAI Bill by 73%

*Last month, I nearly spat out my coffee reviewing a startup's cloud bill. Three people. One MVP. $4,200 in AI API calls. And here's the punchline—60% of those

Read more →
· 9 min read

I Tested GPT-4o, Claude 3.5 Sonnet, and Gemini 1.5 Pro on 1M-Token Documents. My Wallet Still Hasn't

Hot take: Most of you are haemorrhaging cash on AI text processing, and the "best" model is rarely the one you actually need. Let me paint you a picture

Read more →
· 6 min read

I Stress-Tested GPT-5.5 Instant's Hallucination Control on a 15k-Word Doc and the Results Are... Wei

Throwaway account because my main one's tied to my startup and I really don't need investors watching me publicly roast the tools we're paying for. Again

Read more →
· 8 min read

The Hidden Architecture That Makes Cursor Feel Like Magic (And Why Most AI Tools Get It Wrong)

I still remember watching a developer use one of the first AI coding assistants back in 2022. They'd type a prompt, lean back, and wait. Four seconds. Sometimes

Read more →
· 9 min read

I Spent 3 Months Building a Voice Agent with OpenAI's Realtime API — Here's Everything the Docs Don'

I threw away two months of work last week. Two. Whole. Months. Just... gone. The reason? I fundamentally misunderstood how voice interruption works in OpenAI's

Read more →
· 6 min read

I Pitted Two AI Coding Assistants Against Our Legacy Codebase—One Actually Understood It

Last weekend, I did something that felt vaguely unethical: I fed our most cursed legacy module to two different AI coding assistants and watched them fight it o

Read more →
· 9 min read

Why Your AI Chatbot Feels Broken (And Streaming Is the Fix Nobody Talks About)

I remember sitting in a product review at Stripe back in 2019, watching a demo of our shiny new customer support chatbot. The user typed a question. Then nothin

Read more →
· 6 min read

Stop Treating Your LLM Costs Like a Black Box: A FinOps Blueprint That Actually Works

Last quarter, I watched a team burn through 40% of their monthly cloud budget in two weeks. The culprit wasn't an infinite loop or a rogue Kubernetes cluster. I

Read more →
· 12 min read

When AI Agents Invent Their Own Language: What GPT-5.6's Emergent Behaviors Mean for the Rest of Us

Last month, I found myself staring at an internal research briefing that made me put down my coffee mid-sip. Not the dramatic "spit take" thing people joke abou

Read more →
· 8 min read

How Tokenizer Vocabulary Gaps Are Quietly Bleeding Your API Budget (I Have the Receipts)

Last Wednesday at 2:47 AM—I know the timestamp because Slack kindly reminded me—I was staring at our AWS billing dashboard with that sinking feeling you get whe

Read more →
← Previous 1 ... 4 5 6 7 8 ... 42 Next →