Blog

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

· 8 min read

I Cut Our AI Token Costs by 62% Using "Token Maze Theory" (And You're Probably Making the Same Mista

Last Thursday at 3 PM, our finance person dropped a screenshot in the company Slack. Our AI inference cost curve had gone nearly vertical — 4x increase over thr

Read more →
· 8 min read

I Let AI Solve a Hard LeetCode Problem in 23 Seconds—and Questioned Everything

Last week’s LeetCode contest, I hit a wall. A Hard DP problem. Forty-seven minutes of my life, gone. I submitted a solution that *technically* worked—then it ti

Read more →
· 9 min read

I Let an AI Refactor a 3,000-Line "Code Dumpster Fire" at 2 AM — Here's What Happened

Honestly, I almost threw my keyboard out the window that night. December 11, 2024. 2 AM. I'm staring at a file called utils.py that's been haunting me for two y

Read more →
· 6 min read

I Cut My AI Chatbot's Response Time from 11 Seconds to Under 1 Second — Here's the Stupid-Simple Fix

Last Tuesday, I made a change that dropped our customer service bot's response time from 11.3 seconds to 0.9 seconds. My boss thought I'd rebuilt the entire arc

Read more →
· 9 min read

I Fixed My RAG System's Hallucination Problem by Beating Up Bad Documents

Last year I built an enterprise knowledge base Q&A system. During testing, the RAG accuracy was a miserable 67%. Users weren't gentle: "Why does your AI keep ma

Read more →
· 9 min read

I Let AI Build an E-Commerce Backend in 20 Minutes—Then Watched It Give Admin Rights to Every Visito

You're going to think I'm exaggerating. I'm not. Last month, I built an entire e-commerce admin panel without writing a single line of SQL or calling a single A

Read more →
· 10 min read

When 1000 AI Function Calls All Time Out at Once: Lessons from a 3-Second Meltdown

Last year during Singles' Day (think Black Friday but bigger), our team's smart customer service system exploded. I mean literally three seconds past midnight

Read more →
· 6 min read

I Made 1,000 API Calls to GPT-4 and Realised Function Calling's "Structured Output" Is a Lie

Last Wednesday at 2:47 AM, PagerDuty woke me up. The 43rd "JSON Parse Failed" alert. I squinted at the monitoring dashboard, and it suddenly hit me — we've been

Read more →
· 7 min read

The Brutal Truth About AI Startups: Why 200 Companies Became 5 in 18 Months

Last December, I attended a rather unusual conference. Closed-door. About thirty AI founders crammed into a room. The organisers threw some numbers on screen th

Read more →
· 8 min read

That PagerDuty Call at 2 AM: How LLM Agents Fill Your Server with Zombie Processes

Last Wednesday at 2 AM, my phone buzzed. PagerDuty. The kind of buzz that makes your stomach drop before you even look at the screen. Server CPU was pegged at 1

Read more →
· 8 min read

I Killed Our API Gateway With a Coffee Cup and 47 Minutes of Downtime

Last Wednesday, 3:12 PM. Our API aggregation platform went dark. For 47 minutes straight. The reason was embarrassingly stupid—one model provider's gpt-4-turbo-

Read more →
· 5 min read

I Cut Our AI Response Time from 8.3s to 1.4s — Here's What Actually Worked

Last Wednesday at 2 PM, we pushed our AI customer service system to production. I hadn't even settled into my chair when the messages started flooding in. Scree

Read more →
← Previous 1 ... 11 12 13 14 15 ... 42 Next →