#Transformer
1945 related articles
·4 min
Google Hybrid Inference Comes to iOS: A Complete Guide to On-Device AI Cross-Platform Deployment
Google Hybrid Inference officially supports iOS, adds Gemma 4 on Android, and Chrome local Web inference nears GA. A deep dive into hybrid inference technology, cross-platform advantages, and developer opportunities.
Read more →
·4 min
Google Hybrid Inference Comes to iOS: A Complete Guide to On-Device AI Cross-Platform Deployment
Google Hybrid Inference now supports iOS, adds Gemma 4 on Android, and Chrome local Web inference nears GA. A deep dive into hybrid inference technology, cross-platform advantages, and developer opportunities.
Read more →
·2 min
The Same Question Behind Six Claude Projects: Why Not Give It a Try?
A developer completed six projects with Claude, all starting from one question: Why not? Exploring the creator's mindset in the AI era and how to build efficient AI-assisted development habits.
Read more →
·2 min
Genspark AI: A Deep Dive into the All-in-One AI Workspace Built on Claude
Explore how Genspark AI leverages Anthropic's Claude to build an all-in-one AI workspace, with insights on team strategy, tech choices, and the competitive landscape.
Read more →
·3 min
Deep Conversation with Gemini's Four Co-Leads: Technical Roadmap, Current State, and Future Direction
Google Gemini's four co-leads — Jeff Dean, Noam Shazeer, and others — discuss Gemini's technical roadmap, multimodal capabilities, Agent direction, and future strategy in a rare joint conversation.
Read more →
Tutorials·3 min
Agent Tuning: A Complete Guide to Training LLMs with Agent Capabilities
A deep dive into Agent Tuning principles and practices, covering why Agent training is needed, the evolution from Prompt to RAG to Agent, development workflows, and cost assessment for private deployment.
Read more →
Tutorials·2 min
Getting Started with RAG: What Is Retrieval-Augmented Generation and How Does It Solve LLM Hallucination?
RAG (Retrieval-Augmented Generation) is the core solution for LLM hallucination. Learn RAG concepts, how it works, three causes of hallucination, and the complete learning path from basics to Knowledge Graph RAG.
Read more →
Tutorials·2 min
MCP Protocol in Practice: Building an AI Investment Analysis Agent with TradingView + Notion
A detailed guide on MCP protocol vs Skills, integrating TradingView and Notion MCPs to build an automated investment analysis Agent with market scanning, backtesting, and report generation.
Read more →
Tutorials·3 min
Alibaba Cloud Bailian Platform Hands-On: Complete Tutorial from API Calls to Multi-Turn Conversations
Complete tutorial on Alibaba Cloud Bailian platform covering API Key setup, Qwen model calls, streaming output, multi-turn conversation principles, and prompt engineering with four roles.
Read more →
Tech Frontiers·1 min
Gemini 3.5 Flash Surpasses Pro in Vision Capabilities, 6x Faster Inference
Roboflow benchmarks show Google Gemini 3.5 Flash outperforms the flagship Gemini 3.1 Pro on multiple vision tasks with ~6x faster inference, delivering a cost-effective multimodal AI solution.
Read more →
Deep Dives·4 min
AI Hallucinations: Why Large Language Models Inevitably "Make Things Up" and How to Deal With It
Deep dive into AI hallucination's three root causes: training objective flaws, exposure bias, and probabilistic generation. Covers classification and practical mitigation strategies including RAG.
Read more →
Tutorials·3 min
Matt Pocock's AI Coding Workflow: A Complete Methodology from Ideation to Delivery
Deep dive into Matt Pocock's AI-assisted coding workflow: Grill Me consensus building, PRD generation, Tracer Bullet vertical slicing, AFK execution, and Deep Modules architecture design.
Read more →
Deep Dives·2 min
The "Worse is Better" Philosophy of Large Model Design: Why Simple and Brutal Beats Refined and Complex
Analyzing the "worse is better" philosophy in large model architecture: why DeepSeek V4 dropped N-gram, why Transformer dominates AI, and three iron laws of simple, efficient model design.
Read more →
Expert Opinions·3 min
Being Underestimated Is Freedom: A Contrarian Competition Philosophy for the AI Era
Exploring the contrarian strategy of 'being underestimated is freedom' in AI. From OpenAI to DeepSeek to Cursor, why staying under the radar beats standing in the spotlight.
Read more →
Deep Dives·3 min
Complete Guide to LLM Training: Pre-training, SFT Fine-tuning, and Preference Alignment Explained
Complete guide to the three core LLM training stages: pre-training, supervised fine-tuning (SFT), and preference alignment (DPO/PPO), covering LoRA, distillation, quantization, and pruning.
Read more →
Tutorials·2 min
Ollama Local LLM Deployment: From Installation to Conversation in Three Steps
Learn how to deploy LLMs locally with Ollama in three simple steps: install, choose a model, and run. No coding required, supports offline use, and completely free.
Read more →
Expert Opinions·3 min
Is Learning to Code Still Worth It in the AI Era? An Honest Answer from an Atlassian Engineer
Can AI write code instantly—so is coding still worth learning? An Atlassian engineer breaks down the truth behind tech leaders' claims and AI coding limitations.
Read more →
Industry Insights·2 min
AI Writes Code 2x Faster, But Maintenance Costs Triple: A Guide to Breaking the Efficiency Paradox
AI coding tools double development speed but triple maintenance costs. This article analyzes quality issues, technical debt accumulation, and provides actionable strategies to balance efficiency with maintainability.
Read more →
Tutorials·2 min
Complete AI Comic Drama Production Workflow: A Systematic Methodology from Script to Final Cut
Complete guide to AI comic drama production workflow covering LLM scriptwriting, AI image generation on platforms like Jimeng, and post-production editing—a systematic methodology for creators.
Read more →
Deep Dives·3 min
Deep Dive into How Claude Code Works: A New Programming Paradigm Driven by the Agent Loop
Deep dive into how Claude Code works, including the Agentic Loop, automatic context compaction, tool calling, and permission modes that power autonomous AI programming.
Read more →