#Via 1.0
189 related articles
·4 min
From Enter to First Token: Decrypting the Full LLM Inference Pipeline (Autoregression, KV Cache & Decoding Strategies)
From pressing Enter to the first character appearing, what happens inside an LLM? This article breaks down autoregressive generation, KV cache acceleration, and decoding strategies like temperature, Top-k, and Top-p.
Read more →
·4 min
GPT-5.6 In-Depth Analysis: Model Architecture, Performance Benchmarks, and a Complete Guide to the Agentic Era
A comprehensive analysis of GPT-5.6: the Sol/Terra/Luna product-line positioning, MoE architecture, 1.5M token context, coding agent benchmarks, and the shift from Chatbot to Agent.
Read more →
·4 min
Learn ML Free at Public Libraries: A Complete Guide to O'Reilly Tech Book Resources
Getting O'Reilly machine learning books free at public libraries? It's no myth. This article reveals hidden tech learning resources at libraries, including online platform subscriptions and digital database access, helping self-learners build AI knowledge at zero cost.
Read more →
·4 min
Gemini Omni Hands-On: A Deep Dive into Google's Omni-Modal Video Generation Capabilities
An in-depth hands-on review of Google's Gemini Omni omni-modal AI model, covering video generation workflows, prompting tips, visual quality, and comparisons with Sora and other competitors.
Read more →
·3 min
Benchmarking LLMs on Smartphones: A Deep Dive into the MELTing Point Benchmark
The MELTing Point paper is the first to evaluate mobile LLM performance in real user scenarios, covering iPhone, Samsung, Pixel and more, testing TinyLlama, Mistral-7B and others—revealing GPU inference gains, 47°C heat warnings, and prefill-decode disaggregation.
Read more →
·4 min
Running Out of Codex Quota? An In-Depth Review of HeyRoute's GPT-5.5 Integration
Codex quota running out too fast, or API costs too high? HeyRoute offers a low-cost AI coding relay via GPT-5.5, with ~1.08s first response and 99.95% success rate. This in-depth review covers its selling points, pricing, and caveats.
Read more →
·3 min
Xiaomi Smart Home Screen 10 In-Depth Review: An AI-Powered Whole-Home Smart Control Hub
Xiaomi Smart Home Screen 10 review: a 10.1-inch display with AI-powered Xiao Ai, compatible with 3,000 smart devices and 261 IoT platforms. Supports scene automation, video calls, IR control, and privacy protection.
Read more →
·2 min
Microsoft Open-Sources .NET Skills: Making AI Coding Agents Master C# Development
Microsoft open-sources dotnet/skills, packaging .NET/C# best practices as structured skills for AI coding agents. Bridges domain knowledge gaps in general LLMs, improving code quality for GitHub Copilot and other tools.
Read more →
·7 min
Training Machine Learning Models from Scratch: A Complete Beginner's Guide
A complete walkthrough of training machine learning models from scratch—covering problem definition, data preprocessing, algorithm selection, hyperparameter tuning, and evaluation, with tool recommendations for beginners.
Read more →
·5 min
DCTS: A Deep Dive into an Open-Source Self-Hosted E2EE Encrypted Communication Platform
DCTS is an open-source, self-hosted instant messaging platform led by an individual developer, integrating E2EE and decentralized architecture across desktop and mobile.
Read more →
·5 min
GPT-5.6 Released: Outperforms Rivals but Halted by Government—Cybersecurity Capabilities Trigger Regulatory Red Line
OpenAI releases GPT-5.6 (Sol/Terra/Luna), beating Anthropic on Terminal Bench at ~40% lower cost. But its cybersecurity capabilities hit danger thresholds, limiting access to trusted partners at government request.
Read more →
·6 min
Grok 4.5 Coding Benchmark: A Deep Dive into Performance, Speed, and Cost
xAI releases Grok 4.5, purpose-built for coding agents. 80 TPS speed, $2/M input tokens, SWE Bench Pro score of 64.7, and 4.2x better token efficiency than Opus 4.8. A deep hands-on review.
Read more →
·5 min
GPT-5.6 Triple Launch: Understanding the Positioning and Key Differences of Sol, Terra, and Luna
OpenAI released three GPT-5.6 models—Sol, Terra, and Luna—covering everything from flagship reasoning to lightweight speed. A deep dive into their positioning, performance differences, pricing, and industry signals.
Read more →
·6 min
Grok 4.5 Hands-On: A Faster, Cheaper Coding Dark Horse — Can It Replace Opus and GPT?
In-depth Grok 4.5 hands-on review: priced at a fraction of Opus 4.8, twice the token efficiency of peers, and coding ability in the top tier. A real-project breakdown of its strengths, highlights, and shortcomings.
Read more →
·5 min
Getting Started with AI Agents: Concepts, Architecture, and Core Components Explained
What is an AI Agent? Starting from Bill Gates' claim about the computing revolution, this article explores AI Agents' intuitive concepts, four core components (LLM+Planning+Memory+Tools), and what Agent development means for programmers.
Read more →
·6 min
GPT Live Full-Duplex, Grok 4.5 Coding, Seedream 5.0 Images: AI Accelerates Across Three Tracks Simultaneously
OpenAI's GPT Live full-duplex voice model, Grok 4.5 coding model with Cursor, and ByteDance's Seedream 5.0 Pro image generation launched together. A deep dive into three AI releases.
Read more →
·6 min
Balancing Cost and Performance in Azure SQL Database: Three Core Strategies Explained
This article breaks down Azure SQL Database's progressive cost-optimization strategy from the free tier to Hyperscale, Serverless auto-scaling, and Elastic Pools, helping teams balance performance and budget.
Read more →
·4 min
Claude Code Getting Started Guide: Complete Installation and Configuration Walkthrough
A step-by-step guide to installing and configuring Claude Code from scratch: Node.js setup, Git Bash, npm install, proxy configuration, and API Key authorization.
Read more →
·4 min
IMGNet: A New Face Verification Approach Challenging Cosine Similarity with Sign Pattern Matching
IMGNet is a face verification model by an independent Indonesian researcher that replaces cosine similarity with sliding window sign pattern matching. At just 10.58MB, it outperforms cosine on LFW and other benchmarks, introducing metric-loss co-design.
Read more →
·2 min
Claude Sonnet 5 Leaked, Zhipu Hits HK$1 Trillion Market Cap: AI Industry Roundup for June 23
June 23 AI roundup: Claude Sonnet 5 leaked with 1M context window, Zhipu hits HK$1T market cap, Alibaba releases Happy Horse 1.1, and Sakana AI launches a multi-model orchestration system.
Read more →