Blog

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

· 7 min read

Transformer & BERT: Key Issues Revisited for AI Devs

Have you ever had that kind of interview? After three months of fall recruitment, I was so sick of answering Transformer and BERT trivia that I could've thrown

Read more →
· 6 min read

LLM Hallucination: A Deep Dive into Causes and Fixes

Can you believe it? Me – someone who thinks they deal with AI every single day – got chills from a paper that was completely fabricated by an AI. Here's what ha

Read more →
· 6 min read

1. Don't Just Focus on r and alpha! Have You Been Burned Too?

Damn, Fine-Tuning DeepSeek with LoRA Nearly Broke Me! So the other day I got a job—fine-tuning DeepSeek for a psychology counseling team to handle multi-turn co

Read more →
· 6 min read

First, Let's Be Clear What Inference Actually Computes

Okay, I've read your article carefully. Most of the technical points are genuine insights from your own practice—no major flaws, the data is fairly solid, and o

Read more →
· 6 min read

10 challenges, each with a real‑world counterpart

Last week, I almost got scolded to tears by my boss. It was over a bad case in our recommendation system: the system recommended a “prostate exam” to a female u

Read more →
· 2 min read

A True Story

Guess what? Recently, several friends came to me asking the same question: “Large language models are so hot right now—how do I actually tune one to do what I w

Read more →
· 6 min read

DeepSeek-R1 Technical Report: Key Insights Explained

To be honest, staring at that loading spinner at three in the morning, just waiting for a technical report to finish loading. Someone asked me if it was worth i

Read more →
· 4 min read

I Tested the Waters of Large Model Training So You Don’t Have To—and My Feet Are Numb

Okay, I've fact-checked and polished the language as you requested. I mainly corrected inaccuracies or overstatements regarding ChatGLM's positional encoding, s

Read more →
· 4 min read

But so what if you buy one?

Let me tell you a true story. I've been writing about AI hardware for ten years now. From the BERT days when people scrambled for V100s like they were Spring Fe

Read more →
· 5 min read

Parallel Strategies for Large Models—Don't Be Intimidated! It's Really Just Three Cuts, and Every On

Okay, no problem. The original text was already great—lively, conversational, and technically on point. It just needed a bit more polish on facts and pacing. I

Read more →
· 6 min read

I. You Thought It Was Empty? It Already Contains a Complete “Sketch”

Lean in. Let me ask you something. You’ve definitely tried this before—same prompt, same model, identical step count and CFG scale, not a single button touched

Read more →
· 6 min read

Let me tell you a true story

Let me tell you a true story. A couple days ago, someone came up to me again: "Bro, is deep learning actually any good for defect detection?" You have to unders

Read more →
← Previous 1 ... 38 39 40 41 42 Next →