Blog

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

· 6 min read

After Writing Dozens of Issues on Visual Generation, These 5 Counter-Intuitive Findings Made Me Sit

Alright, I read the article carefully. Facts and figures are fine—you’ve clearly done your homework on the parameters and results of those specific models. The

Read more →
· 5 min read

1. 1.8 Trillion Parameters and Climbing—But OpenAI Played a Trick

Last month, I did something that sent a chill down my spine. I tossed a corporate financial chart into GPT-4—a tangle of lines, bars, and annotations all jumble

Read more →
· 1 min read

Question 1: Why do large models even need distributed training? Can't I just use a single GPU?

Guess what? When I wrote my last GPT tutorial, my inbox was flooded with messages from readers: "Hey master, I've digested the model theory, but I want to train

Read more →
· 6 min read

LLM Inference Optimization: KVCache, FlashAttention, MQA, GQA & More

A while ago, a friend came to me with a complaint. He had just finished training a 7B model, deployed it happily, and as soon as the user numbers picked up, the

Read more →
· 1 min read

AI Large Models?

My biggest pitfall this year was fooling myself. Can you believe it? At the beginning of the year, I got my hands on the Gemma 3 12B model, and I was thrilled—f

Read more →
· 4 min read

The first time I used a large model to write copy, I was completely dumbfounded

I've been working on large language models for over half a year now, been through three hundred rounds of torment at the hands of Transformers—and today, I'm sp

Read more →
· 6 min read

You Think Multimodality Is Just Looking at Pictures and Reading Words? Naive!

Have you ever personally written a shopping list in such wild, scrawling handwriting that even you had to squint for half a day to figure it out? Then I snapped

Read more →
· 6 min read

Revised Article

I have a friend who spent a whole year chanting, "Cursor is my god." He renewed his Ultra subscription for two months, and with the API usage fees, he was burni

Read more →
· 6 min read

First slap in the face: scattered requirements mean scattered output

Have you ever had that frustrating feeling? You're reading a web novel, you follow it for over two thousand chapters, then put it down for a few months. When yo

Read more →
· 4 min read

I’m sitting there staring at my RTX 3090, feeling like a million ants are crawling under my skin

Alright, over to you. This is the corrected version after fact-checking — keeps the whole rant-and-recommend vibe, but with tighter data and a smoother narrativ

Read more →
· 6 min read

Prompt Caching: The Only Guide You’ll Ever Need

I read your article again. The core arguments and most of the experiences are solid—there are just a few factual details that could be more precise, and some ph

Read more →
· 3 min read

Let me start with a story—then you'll understand why I went all in on fine-tuning

After two years of working on vertical domain large model fine-tuning, my deepest realization is this—this thing really isn't just about piling on parameters

Read more →
← Previous 1 ... 35 36 37 38 39 ... 42 Next →