Blog

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

· 6 min read

Large Language Model Programming Capability Evaluation: October 2025 Rankings – I Changed My Testing Method

Last Friday night, I was coding in a café when a guy in a plaid shirt sitting next to me was losing his mind staring at his screen—error messages flooding the c

Read more →
· 6 min read

When AI Opened Its Eyes for the First Time, What Did It See?

A few days ago, I did something particularly boring—I threw a meme image of "programmer before fixing a bug vs after fixing a bug" at ChatGPT. It was completely

Read more →
· 6 min read

Let's start with the conclusion: Yes, but not in the way you imagine

Let me tell you a true story. My cousin is a high school sophomore flunking programming class. Ask him, "What's a variable?" and he'll stammer and mumble. Last

Read more →
· 6 min read

Why not let all parameters work together?

Okay, let me fact-check, correct the data, and remove the AI tone to make the article more natural. Have you ever had this experience? You have a team of a hund

Read more →
· 6 min read

Transformer trains 5x faster than LSTM, cuts costs by 80%

When I first read the paper *"Attention is All You Need"* back in 2018, my reaction was brutally honest. I stared at the screen, and one thought echoed in my mi

Read more →
· 5 min read

The Communication Optimization Secrets in Megatron-Core Nobody Tells You

Last year, I trained a 70B model, spending hundreds of thousands of GPU hours, and I was thrilled, thinking I was finally going to get results. But then the nei

Read more →
· 7 min read

Just Interviewed a Candidate That Made My Blood Pressure Spike! My Hands Are Still Shaking!

Okay, got your request. As an editor, I carefully reviewed this article, fact-checked it, and polished the wording. Below is my revised version, aiming to keep

Read more →
· 6 min read

1. Quantization Is the Most Practical Path, But Don't Expect It to Be Lossless

To be honest, a few days ago I did something particularly foolish—I dug out my old GPU with only 8GB of VRAM and tried to run a local large language model. I me

Read more →
· 6 min read

"Can't Generate a Damn Thing" — My Ten-Year Blood, Sweat, and Tears with GANs, and How It All Ended

In 2014, the first time I read the GAN paper, I almost smashed my computer. To be honest, back then I'd just started working in image generation, and I figured

Read more →
· 6 min read

I. Saying KV cache is just a cache only sees one corner of the picture

You must have heard someone say: "KV cache? It's just a cache—what's there to talk about?" I’d bet ten to one that whoever says that has never written an infere

Read more →
· 6 min read

So what exactly does the projector encode? It gets even stranger.

Isn't it strange? I stared at that embedding space visualization for an entire afternoon without blinking. On the left was the figure from the paper—red dots, t

Read more →
· 5 min read

But "Catching Up" Might Be an Illusion

Alright, here's the fact-checked and edited version. Major changes: replaced non-existent models (GLM-5.2, DeepSeek V4, GPT-5, Claude 4, etc.) with real models

Read more →
← Previous 1 ... 28 29 30 31 32 ... 42 Next →