Blog

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

· 6 min read

A Pandemonium of Experts: What the Hell Is an MoE Large Model?

To be honest, the impulse to write this came from the embarrassment of being stumped. The other day, a friend suddenly asked me: "What's so great about MoE? Why

Read more →
· 5 min read

That Spring of 2020, I Nearly Got Sick From Practicing for the Detection Competition

In the spring of 2020, I did something incredibly “dumb”—I spent half a year grinding mAP until I felt like throwing up every time I saw the COCO dataset

Read more →
· 4 min read

How to Reproduce InstructGPT / RLHF Correctly

I've been hitting every possible pitfall with RLHF since last year, and today I'm spilling it all for you. You know what? The first time I ran PPO, I almost thr

Read more →
· 5 min read

Understanding RoPE: LLM Positional Encoding

Hey, you know what? The first time I ran into the trouble with positional encoding was during a text generation experiment. Same prompt, I just tweaked the word

Read more →
· 6 min read

So Which Tools Actually Deliver?

I Found a Tool That Can "See Through" the Transformer's Brain! It Completely Wrecked Me 😭 Remember the first time you tried to learn Transformer and had a compl

Read more →
· 6 min read

Large Model Interview Guide: Function Call, MCP & A2A

Believe it or not? One casual follow-up question from an interviewer can bring your entire answer—no matter how brilliantly you started—crashing down to zero

Read more →
· 1 min read

Instead, I ask myself: *Can I explain this clearly?* If I can't, I don't rush to tune anything

Through all these years of working with models, one lesson has sunk in deeper than any other: seven years of learning, countless pitfalls, endless hyperparamete

Read more →
· 6 min read

Large Model Distributed Training: First, Learn How to Get 10,000 GPUs to Work for You!

Okay, I'll admit it. I used to be a "single-GPU warrior." Back when I saw people training hundred-billion-parameter models, I thought: "It's just stacking GPUs

Read more →
· 6 min read

AI Agents vs. LLM Agents: A Deep Dive

Bro, you still think ChatGPT is the endgame of AI? I thought the same way last year. It can write code, draft copy, and chat with you until three in the morning

Read more →
· 6 min read

Let's start with the verdict: What exactly did GPT-4 upgrade?

Oh my god! GPT-4 is finally here, and this time, I absolutely cannot sit still! That night, I was hunched over my computer tweaking code when my phone started b

Read more →
· 7 min read

Deep Dive into Superpowers and gstack: AI-Powered Dev Tools

Believe it or not, at the beginning of last year, I was an absolute fool. The whole world was shouting "AI is going to replace programmers," and I was like a ca

Read more →
· 6 min read

I Used AI to Write Novels and Made a Steady $8,000 in 3 Months! But You’re Making the First Mistake!

Okay, got the instructions. As an editor, I’ll fact-check and polish this article, aiming to: correct factual errors, remove the AI vibe, and keep the substance

Read more →
← Previous 1 ... 33 34 35 36 37 ... 42 Next →