#SFT
187 related articles
Product Reviews·3 min
Kimi K2.6 In-Depth Review: A Complete Breakdown of Its Coding and Agent Capabilities
In-depth review of Kimi K2.6's coding, Agent collaboration, and visual development capabilities. #1 open-source on SWE-Bench Pro, 300 parallel sub-agents, API priced at 1/3 of competitors.
Read more →
Product Reviews·1 min
Gemini 3.5 Flash Falls Flat: Great Benchmarks, Terrible Real-World Performance, and a Buggy CLI
Gemini 3.5 Flash benchmarks look great but it's the only model that failed real-world coding tests. Prices surged 20x with poor token efficiency.
Read more →
Research·3 min
Inside Cursor Composer 2 Training: A Complete Breakdown of Its Distributed Reinforcement Learning Architecture
Deep dive into how Cursor trained Composer 2 on Fireworks: async pipeline architecture, MoE numerical precision challenges, Router Replay, and global distributed GPU coordination.
Read more →
Product Reviews·2 min
Termius SSH Client Pain Points Analysis: Are There Better Alternatives in 2024?
In-depth analysis of Termius SSH client UX pain points, exploring why developers give public feedback, comparing alternatives like Tabby and iTerm2, and examining SSH tool market competition.
Read more →
Product Reviews·2 min
Cursor Composer 2.5 Released: Three Core Upgrades and a New AI Programming Experience
Anysphere releases Cursor Composer 2.5 with three core upgrades: higher intelligence, sustained long-task performance, and reliable complex instruction following, plus limited-time double free quota.
Read more →
Tech Frontiers·2 min
Qwen3.7 Max Deep Dive: 1T Parameter MoE Architecture with Full Agent Framework Compatibility
Deep analysis of Alibaba's Qwen3.7 Max: 1T-parameter MoE architecture, 256K context window, leading agent programming capabilities, full framework compatibility, and the model-vs-harness industry debate.
Read more →
Tutorials·2 min
DeepSeek R1 Usage Guide: Prompt Techniques & Practical Tips (2025)
A detailed guide to DeepSeek R1's reasoning capabilities and prompt techniques, covering reasoning vs. general models, core capabilities, and practical prompt strategies for 2025.
Read more →
Tutorials·1 min
AI Agent Interview Focus Comparison: ByteDance vs. Tencent vs. Alibaba — Differences in Approach & Preparation Strategies
Deep comparison of AI Agent interview focuses at ByteDance, Tencent, and Alibaba: ByteDance drills ReAct implementation & RLHF details, Tencent emphasizes MCP protocols & memory systems, Alibaba focuses on multi-Agent architecture & business deployment.
Read more →
Tutorials·3 min
2026 AI Learning Roadmap: 3 Proven Paths + A 4-Step Action Checklist (With Complete Technical Framework)
How to learn AI in 2026 without wasting time? This guide covers 3 proven paths — AI Agent customization, vertical specialization, and full-stack LLM development — plus a 4-step action checklist.
Read more →
Tutorials·2 min
2026 AI Large Language Model Learning Roadmap: Complete Guide from Zero to Agent Development
2026 AI large model learning roadmap: from Python basics and prompt engineering to RAG knowledge base, Agent development, and fine-tuning deployment. A complete 42-episode full-stack tutorial with three proven paths for enterprise AI deployment.
Read more →
Product Reviews·3 min
GitHub 8K Stars: Deep Dive into the Most Comprehensive LLM Resource Repository
Deep analysis of the GitHub project awesome-LLM-resources covering multimodal generation, AI Agents, MCP protocol, model training/inference, o1 models, and SLMs—a community-verified 8200+ Star LLM learning resource hub.
Read more →
Product Reviews·3 min
8K Stars on GitHub: Deep Dive into the Most Comprehensive LLM Resource Repository
Deep analysis of the awesome-LLM-resources project (8200+ GitHub Stars), covering multimodal AI, Agents, MCP protocol, model training, o1 reasoning, SLMs, and more for LLM practitioners.
Read more →
Product Reviews·4 min
Cube Studio Deep Dive: Tencent's Open-Source One-Stop MLOps Platform
Deep dive into Cube Studio, Tencent Music's open-source one-stop AI platform, covering architecture design, distributed training, large model fine-tuning and inference, and domestic chip adaptation.
Read more →
Research·4 min
Continual Harness: AI Automatically Builds Scaffolding to Beat Pokémon RPGs
Princeton and Google DeepMind propose Continual Harness, enabling LLM agents to automatically build and optimize scaffolding to beat multiple Pokémon RPGs without human intervention, cutting costs by 40%.
Read more →
Deep Dives·3 min
What Are Large Language Models? A Deep Dive into Parameters, Models, and the Essence of AI LLMs
What exactly is a large model? This article explains the essence of LLMs from the core concepts of "models" and "parameters," covering GPT parameter scales, vector dimensions, and open-source model selection.
Read more →
Product Reviews·3 min
Cursor Composite vs Windsurf SWE 1.5: Three Rounds of Real-World Testing to Determine the Best AI Coding Model
Three progressive real-world tests comparing Cursor Composite and Windsurf SWE 1.5 proprietary AI coding models across HTML games, e-commerce pages, and full-stack systems.
Read more →
Deep Dives·3 min
Alibaba's QwQ-32B Open-Sourced: How 32B Parameters Rival DeepSeek R1's 671B
Alibaba's open-source reasoning model QwQ-32B achieves performance rivaling DeepSeek R1 (671B) with only 32B parameters through a two-stage reinforcement learning strategy on verifiable tasks.
Read more →
Deep Dives·3 min
Reinforcement Learning Drives AI Reasoning Evolution: From Imitator to True Thinker
How RL, Self-Play, and Verifiers work together to evolve LLM reasoning — driving the leap from SFT imitation to true System 2 deep thinking.
Read more →
Deep Dives·3 min
The Evolution of LLM Reasoning: A Complete Guide from Chain-of-Thought to DeepSeek-R1
A systematic overview of LLM reasoning evolution, covering Chain-of-Thought, Tree-of-Thought, OpenAI o1, and DeepSeek-R1, with insights from the Awesome-LLM-Reasoning project.
Read more →
Product Reviews·3 min
awesome-LLM-resources: A Comprehensive Analysis of the 8,200-Star LLM Learning Resource Repository on GitHub
In-depth analysis of the 8,200-star GitHub project awesome-LLM-resources, covering multimodal generation, Agents, model training, MCP protocol, and more — a one-stop LLM learning guide.
Read more →