Blog

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

· 8 min read

I Tested GPT-5.6 on 47 Dynamic Programming Problems — Here’s Where It Shines and Where It Falls Flat

Last week, I threw 47 DP problems at GPT-5.6’s API. Twelve of them crashed and burned. The worst offender? A knapsack variant where the model confidently handed

Read more →
· 10 min read

Your GraphRAG Is Still Hallucinating—Here's Why and What Actually Helps

Last Thursday at 2 a.m., I sat staring at my screen with a cold knot forming in my stomach. An e-commerce client's GraphRAG system had just told them their "Q2

Read more →
· 6 min read

I Reverse-Engineered Cursor's Source Code to Understand Its Background Agent Coroutine Scheduler

Last Tuesday, I was debugging a weird one. Cursor's Background Agent claimed it was idle, but my CPU was pinned at 40%. I stared at htop for ten minutes, fans s

Read more →
· 5 min read

I Rewrote a 3-Year-Old Order System in 4 Days Using GPT-5.6's API — Here's What Actually Happened

Last week, I rebuilt our order processing system. The one that's been running for three years. Seventeen microservices. Over 2,300 files. Four days. Last year

Read more →
· 5 min read

Multimodal Models Are Broken: 5 Real-World Lessons from Someone Who Got Burned

Let me set the scene. You're at a desk, coffee in hand, staring at a screenshot of a product spec table. You ask a multimodal model: "Can I customize the dimens

Read more →
· 6 min read

I Tested 5 OpenAI-Compatible APIs: Function Calling and Streaming Are Not as Compatible as They

Last Wednesday, I nearly launched my MacBook into the Spree. I’m not messing about. I’d spent three hours debugging what I was sure was a code problem—turns out

Read more →
· 6 min read

I Tested GPT-5's "Thinking Mode" on 50 Math Proofs — It Confidently "Proved" 1=0 Seven Times

Last week I fed GPT-5's Thinking mode 50 graduate-level math proofs. Seven of them ended with the model confidently "proving" that 1 equals 0 — complete with La

Read more →
· 4 min read

I Let Claude Code Loose on My Legacy Codebase. It Was a Beautiful Disaster.

Last month, I tried to get Claude Code to refactor a legacy monolith into a service-oriented architecture. Spoiler: I spent the next 4 hours unborking git

Read more →
· 7 min read

Agent Engineer Interview Questions on Tool Use

A friend texted me late last night. He said he was training a group of interviewers from several big tech companies for Agent positions. He flipped through the

Read more →
· 4 min read

Meituan LLM Algorithm Interview: 3 Tough Function Call Questions

I’d barely sat down, my back not even touching the chair. The interviewer glanced at my resume, and when his eyes landed on the “tool calling” project experienc

Read more →
· 5 min read

The First Real Question: Is This Thing Just Another Black Box?

"Let me tell you something—I did something absolutely insane recently. I spent just three yuan, the price of a cheap cup of milk tea, and trained an AI model fr

Read more →
· 3 min read

I Told My Team to Stop Writing Code for 2 Weeks – The Results Changed Everything

Honestly, I was wrong. A few months ago, I thought I had it all figured out. I mandated GitHub Copilot Enterprise across our 40-person engineering team. It felt

Read more →
← Previous 1 ... 18 19 20 21 22 ... 42 Next →