Blog

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

· 7 min read

Multi-Agent Memory Sharing in GPT-5.6: The Feature That's Not Actually a Feature

Last Tuesday, I watched three AI agents have a full-on identity crisis over a client's company name. Agent A was adamant it was "ByteDance." Agent B insisted on

Read more →
· 8 min read

Your GPU Cluster Is Burning Cash: My Bloody Battle with MoE Communication on Heterogeneous Hardware

Last Tuesday, our cluster's All-to-All latency spiked to 800ms, and my boss's face went greener than an A100's cooling shroud. Here's what that actually means

Read more →
· 12 min read

I Reverse-Engineered GPT-5.6 Ultra Mode's Task Orchestration — It's More Human Than We Thought

Last Wednesday, 2 AM. I'm debugging a multi-agent coordination system. CUDA out of memory. Again. While waiting for the model to reload, I stared at the task al

Read more →
· 9 min read

I Tested Cursor, Copilot, and Claude Code on Multi-File Edits — One Made Me Almost Quit My Job

Last week, I did something stupid. I let three AI coding assistants tag-team the same microservice project. The result? One wrote API docs backwards, another di

Read more →
· 7 min read

My AI Agent Refunded $300 Without Permission — And Other Horror Stories From Production

Last Thursday at 2:47 AM, PagerDuty ripped me out of a perfectly good dream. Our customer support AI agent had just refunded a user $300. On its own. The reason

Read more →
· 11 min read

I Turned Apache APISIX into an AI Gateway and It Tripled Our QPS While Saving Two Servers

Last November, I took on a gig that nearly broke me—rebuilding the API gateway for an AI startup that was haemorrhaging money. They'd just integrated GPT-4 and

Read more →
· 10 min read

I Processed 1.2M Records with OpenAI's Batch API for $3.70 — and I'm Never Going Back

Last month, I ran 1.2 million records through OpenAI's Batch API. When the bill came, I nearly spat coffee all over my monitor. Three dollars and seventy cents

Read more →
· 8 min read

I Let AI Write 40% of My Code for 4 Months—Here's What Actually Happened

Last Wednesday, I was up until 1am messaging a backend engineer friend. He'd just spent three days building an internal data processing tool, only to discover t

Read more →
· 7 min read

I Let AI Refactor 47 Files in 11 Minutes — Here's What Broke (And How to Avoid It)

Last week I refactored 47 files in a legacy codebase. Took me... okay, I'll be honest. Not kidding. Cursor's multi-file editing compressed two days of work into

Read more →
· 8 min read

Your Vector Search Keeps Failing Because You're Doing Hybrid Retrieval Wrong

Last month, I watched a CTO's face go from excited to horrified in about 4.7 seconds. They'd just launched their shiny new semantic search feature, and someone

Read more →
· 7 min read

I Almost Nuked Our Production Database Last Wednesday. AI Coding Tools Need Guardrails.

Last Wednesday at 11 PM, I nearly deleted our production database. Not exaggerating. The AI-generated rm -rf command was sitting right there in my terminal, cur

Read more →
· 8 min read

I Deleted 500 Lines of Business Logic by Trusting AI's "Long Context Miracle"

Last Tuesday, I dragged a 3000-line order-service.ts file into Cursor 0.42.3 and asked it to "clean things up." Midway through my coffee, I noticed something ho

Read more →
← Previous 1 ... 12 13 14 15 16 ... 42 Next →