#SFT
153 related articles
·4 min
Reinforcement Learning for AI Agents: A Deep Dive into RLHF and Agentic RL
A deep dive into RL for AI agents: from RLHF to Agentic RL, covering PPO vs. GRPO, sparse rewards, tool-calling optimization, and verifiable rewards.
Read more →
·7 min
Demystifying Claude Code's Harness in 60 Lines of Python: The Core of AI Coding Tool Performance Differences
The same model scores 77% in Claude Code but jumps to 93% in Cursor—the only variable is the Harness. This article dissects how AI coding tools work in 60 lines of Python.
Read more →
·7 min
Andrew Ng's Prompt Engineering Course Essentials: Core Methodology Every Developer Must Learn
An in-depth analysis of the essentials of Andrew Ng and OpenAI's ChatGPT Prompt Engineering course. Covers the difference between base and instruction-tuned models, two core prompting principles, and how to wield LLM APIs to build apps.
Read more →
·7 min
LLM Evaluation: The Testing Industry's Scarcest Career Pivot and the Timing to Enter
LLM evaluation roles are growing over 100% year-over-year, with top companies offering 50K/month yet unable to fill positions. This article explores how testing pros can seize the window.
Read more →
·7 min
The Agent Engineer Transition Roadmap: A Deep Dive into Three Core Skill Systems
Want to become an Agent engineer? This article systematically covers three core skill tracks—LLM fundamentals, LangChain architecture development, and enterprise deployment—to help you avoid detours.
Read more →
·6 min
GPT-5.6 Three-Model Launch: Soul/Terra/Luna Tiered Strategy and the AI National Security Game
OpenAI previews the GPT-5.6 series — Soul, Terra, and Luna — with a massive 1.5M-token context. In-depth analysis of coding leaps, the Fable 5 national security game, the heating U.S.-China AI race, and workflow economics.
Read more →
·7 min
Sakana Fugu vs GLM 5.2 Hands-On Test: Who Can Truly Challenge Top-Tier AI Models?
A head-to-head hands-on test of Sakana Fugu vs GLM 5.2 based on real Hermes agent workflows. Covering tool calling, frontend generation, and code improvement to reveal each model's true performance, speed, and value.
Read more →
·7 min
LangChain Hands-On Guide: From LLM Calls to Agent Development
Master LangChain from scratch: the three limitations of LLMs, init_chat_model unified interface config, the Message type system, and the path from LLM calls to Agent development.
Read more →
·2 min
The Truth Behind AI Benchmark Leaderboards: Real-World Performance Is the True Moat
Why are AI benchmark leaderboards increasingly unreliable? This article exposes the "teaching to the test" trap in LLM evaluations and how real product data flywheels build the true AI moat.
Read more →
·3 min
16GB VRAM Showdown: Ornith 35B vs Qwen 35B — Full Benchmark Comparison
Ornith 35B vs Qwen 3.6 35B on 16GB VRAM: 24+ hours of benchmarks covering inference speed, 256K context, tool calling, HumanEval, and real coding challenges.
Read more →
·7 min
Free Mermaid Diagram Editor: An Essential Code-Based Diagramming Tool for Developers
Explore the core features and use cases of the free Mermaid Diagram Editor. Supporting flowcharts, sequence diagrams, Gantt charts and more, it follows the 'diagrams as code' philosophy to enable version-controlled technical documentation for developers and architects.
Read more →
·7 min
Tripadvisor AI Summaries 'Whitewashing' Problematic Hotels? Essential Safety Concerns for Travelers
Tripadvisor's AI review summaries are generating positive assessments for hotels with safety hazards while downplaying critical warnings. Deep analysis of causes and practical user protection tips.
Read more →
·6 min
Coze from Scratch: A Complete Guide to Building Multi-Agent Collaboration
A detailed guide to Coze's core features: cross-platform interoperability, the Skills system, multi-agent collaboration, and workflow building. Compare Coze and Dify to build practical AI apps with zero coding.
Read more →
·7 min
Metacognitive Feedback: Using Reinforcement Learning to Help LLMs Accurately Express Uncertainty
LLMs are often overconfident and prone to hallucination. How can AI learn to say "I'm not sure"? This article explains the reinforcement learning approach with metacognitive feedback and how calibrating confidence boosts LLM trustworthiness.
Read more →
·6 min
GPT-5.6 Released: Three-Tier Soul/Terra/Luna Lineup, Orchestration Baked Into the Model
OpenAI releases the GPT-5.6 series with Soul, Terra, and Luna models. Ranked first on Terminal Bench coding evaluation, Ultra mode natively bakes agent orchestration into the model, while revealing Agentic Trace data as the core competitiveness of next-gen AI training.
Read more →
·6 min
Deep Dive into GPT-5.6 Ultra's Sub-Agent Architecture and Ten Key AI Industry Trends
In-depth analysis of GPT-5.6 Ultra's sub-agent collaborative reasoning, the global rise of Chinese AI models, world-model evaluation gaps, and AI's real-world deployment challenges and bubble warnings.
Read more →
·3 min
Why Does Chain-of-Thought (CoT) Boost Reasoning? A Four-Layer Deep Dive
A four-layer breakdown of why Chain-of-Thought (CoT) boosts LLM reasoning: compute allocation, external working memory, pretraining pattern activation, and DeepSeek R1 RL evidence.
Read more →
Amazon MTurk Closes to New Customers: …
·4 min
Amazon MTurk Closes to New Customers: The End of the Crowdsourcing Era and the AI Revolution
Amazon MTurk stops accepting new customers after nearly 20 years. Explore its legacy in AI training and academic research, and how LLMs are reshaping the data annotation industry.
Read more →
·3 min
Unsloth v0.1.45-beta Released: 2x Faster LLM Fine-Tuning with 70% Less VRAM
Unsloth v0.1.45-beta (PyPI: 2026.6.2) delivers 2x faster LLM fine-tuning and up to 70% VRAM reduction. Now at 67.9k GitHub stars, upgrade via pip install.
Read more →
·2 min
Zhipu GLM 5.2 Deep Dive: Can Open-Weight Models Challenge Top Closed-Source AI?
Zhipu GLM 5.2 review: open weights released within 24hrs, built for long-horizon Agent tasks. Strong benchmarks, standout writing & frontend design, at a fraction of closed-model pricing.
Read more →