Blog

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

· 7 min read

I Got Woken Up at 2:47 AM by PagerDuty — Here's What OpenAI's API Docs Don't Tell You About Error Ha

Last Wednesday at 2:47 AM, my phone started screaming. Not a gentle vibration. Full-on, someone-is-dying PagerDuty alert. The service was down. Not the "oh, som

Read more →
· 8 min read

I Spent $300 on Electricity to Benchmark GPT-5.6 Against Claude Opus — and the Results Made Me Quest

Last week I ran a two-day AI benchmark marathon that cost me over $300 in electricity bills. The data was clear: GPT-5.6 crushed Claude Opus by 17 percentage po

Read more →
· 7 min read

I Built an AI Code Reviewer That Only Looks at My Git Diffs (And It's Shockingly Good)

Last week, I was digging through old commits and found something that made me laugh out loud—a 200-line function I wrote three months ago, nested 4 layers deep

Read more →
· 9 min read

I Tested 4 AI Coding Tools for 8 Hours Straight — Here’s Which One Actually Ships Code

Last week at 2 AM, I was staring at yet another production database crash. Seventh time that week. The error logs were screaming too many connections, and I kne

Read more →
· 8 min read

I Refactored 8 Files in 20 Minutes with Cursor — Here's What Actually Works

Last Thursday at 10pm, I rewrote an entire payment module with Cursor. Eight files. Four hundred lines of changes. Twenty minutes flat. Seriously. Twenty minute

Read more →
· 6 min read

How I Cut DeepSeek's Inference Time from 47 Seconds to 9 (And Nearly Broke Production)

Last Tuesday, I found myself standing next to my boss, watching a 200K-token legal contract review crawl through DeepSeek at a glacial pace. Forty-seven seconds

Read more →
· 8 min read

I Stress-Tested DeepSeek's 128K Context Window — It Started Hallucinating at 50K

Last Wednesday at 2 AM, I burst out laughing at my screen. After 97 rounds of conversation, DeepSeek had somehow convinced itself that I wasn't a human who like

Read more →
· 8 min read

I Switched My Chinese NLP Tasks from GPT-4 Turbo to DeepSeek and Cut Costs by 100x (While Improving

I nearly spat coffee all over my keyboard last week. Here's why: I was running both DeepSeek and GPT-4 Turbo on the same Chinese document summarisation task for

Read more →
· 11 min read

I Spent 3 Months Paying 5 AI Coding Assistants—The Most Expensive One Made Me Feel Stupid

23rd November last year. I remember the date because I was still debugging at 2 AM. I had three different IDEs open simultaneously, each with its own AI assista

Read more →
· 7 min read

GPT-5 Caught Its Own Mistake While Debugging My Code — I'm Still Processing This

Last Thursday at 2:47 AM, I stared at my screen with actual goosebumps. GPT-5 Thinking was debugging a Redis distributed lock issue, mid-reasoning, when it sudd

Read more →
· 6 min read

I Tracked Our AI API Costs for 30 Days — The Bill Made Me Physically Ill

Last week, our team nearly choked on our morning coffee when the AWS bill came in. $23,000. In one month. Just from hitting a certain pay-as-you-go LLM API acro

Read more →
· 7 min read

How I Learned to Stop Worrying and Build Resilient OpenAI API Calls

Last November, at 2 AM, my phone exploded with alerts. Our AI customer service system had gone down during Singles' Day—China's biggest shopping event. I pulled

Read more →
← Previous 1 ... 16 17 18 19 20 ... 42 Next →