#knowledge distillation
409 related articles
·2 min
Cursor Code Review Agent Upgrade: 3x Faster, 22% Cheaper
Cursor's code review Agent (Bugbot) gets a major upgrade: 3x faster, 22% cheaper, 10% better bug detection. Explore the improvements, the /review command, and the AI code review landscape.
Read more →
·2 min
An Anthropic Employee's Firsthand Account: How Claude Fable 5 Evolved from Tool to Collaborative Partner
A veteran Anthropic employee shares observations on Claude's evolution from Opus 3 to Fable 5, highlighting four milestone releases and how Fable 5 marks the shift from tool to collaborative partner.
Read more →
·3 min
Pangu Skill: An Open-Source Project That Distills 18 Business Leaders into Callable AI Protocols
Pangu.skill is an open-source project that distills 18 top business leaders' cognitive patterns into callable AI protocols, enabling 24/7 decision analysis.
Read more →
·3 min
Fixing Tool Confusion: A Practical Method to Make DeepSeek v4 Outperform Opus
Deep dive into DeepSeek v4's Tool Confusion problem and its deterministic fix. Repair Logic dramatically improves open-source model tool call accuracy, outperforming Claude Opus 4.7 in practice.
Read more →
·1 min
WWDC Keynote Preview: Complete Siri Overhaul, Major AI Upgrades, and System Performance Optimization
Apple's WWDC keynote set to unveil major system updates including a completely overhauled Siri chatbot, more compelling AI features, and significantly optimized OS performance.
Read more →
·3 min
Guo Yu on the AI Agent Era: The End of Software and the Fate of Knowledge Workers
Former ByteDance engineer Guo Yu analyzes the AI Agent revolution: how Claude Code's Skill feature signals the end of traditional software, the SaaS collapse, and the future of knowledge workers.
Read more →
·3 min
Codex Beginner's Guide: Lessons Learned from 660 Million Tokens of Real-World Usage
Deep dive into OpenAI Codex Agent's core features, Skill ecosystem, context compression, and project-level Harness management tips from 660M tokens of real-world usage.
Read more →
·3 min
Claude Opus 4.8 Identifies Itself as DeepSeek: Data Contamination or Distillation? A Technical Analysis
Anthropic's Claude Opus 4.8 failed within 2 hours of launch, identifying itself as DeepSeek and Tongyi Qianwen in Chinese. Deep analysis of data contamination vs distillation hypotheses and multilingual alignment gaps.
Read more →
·2 min
The "Magic Fatigue" Effect in AI Products: The Hidden Challenge of User Expectation Management
Exploring the "Magic Fatigue" effect in AI products: why users feel AI is getting dumber, how to distinguish real degradation from rising expectations, and strategies for managing user expectations.
Read more →
·2 min
Gemini 3.5 Flash Teams Up with Antigravity: Multi-Agent Collaboration to Build an Entire City
Deep dive into how Gemini 3.5 Flash and Antigravity platform use multi-subagent architecture to design and build a complete virtual city from scratch.
Read more →
·2 min
ChatGPT Generates Over 1.5 Billion Images Per Week — How Images 2.0 Is Reshaping Visual Content Production
OpenAI reveals ChatGPT users generate over 1.5 billion images weekly. Explore how Images 2.0 is transforming visual content creation across branding, design, and education.
Read more →
·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 →
·3 min
Claude Opus 4.8 Released: Comprehensive Upgrades in Judgment, Honesty, and Autonomous Work Capabilities
Anthropic releases Claude Opus 4.8 with three core upgrades: sharper judgment, more honest self-awareness, and longer independent work duration — all at the same price.
Read more →
·2 min
Gemini Spark: Google's AI Workflow Assistant with Deep Workspace Integration
Gemini Spark is Google's AI workflow assistant powered by Gemini 3.5 Flash, deeply integrated with Google Docs, Gmail, and Workspace apps for cross-app task orchestration and office automation.
Read more →
·2 min
Gemini Spark: Google's AI Workflow Assistant with Deep Workspace Integration
Gemini Spark is Google's AI workflow assistant powered by Gemini 3.5 Flash, deeply integrated with Google Docs, Gmail, and other Workspace apps for cross-app task orchestration and boosted productivity.
Read more →
Industry Insights·2 min
AI Product Development in Practice: Model Selection, Building Moats, and Paths to Commercialization
Practical strategies for AI product development: why not to train models from scratch, when to use APIs vs. fine-tuning, building product moats, and the full path from evaluation systems to commercialization.
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 →
Product Reviews·2 min
GPT-5.1 vs Claude Sonnet 4.5 Hands-On Comparison: Coding, Writing, and Creativity Benchmarked
Hands-on comparison of GPT-5.1 vs Claude Sonnet 4.5 across long-form writing, classical poetry, front-end coding, and UI reproduction to help you pick the right AI model.
Read more →
Tech Frontiers·1 min
Gemini 3.5 Flash Achieves a Massive Leap on the GDPval Benchmark
Google Gemini 3.5 Flash surpasses Gemini 3.1 Pro on the GDPval benchmark. The lightweight Flash model leverages post-training techniques to approach frontier-level performance, redefining the balance between quality and cost.
Read more →