#post-training
135 related articles
·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 →
·4 min
Ternlight: A 7MB Browser-Side Embedding Model for Server-Free Semantic Search
Ternlight is a 7MB WebAssembly-based browser-side text embedding model requiring no server or GPU. Explore its tech, use cases, and tradeoffs for private, offline semantic search.
Read more →
·6 min
GLM 5.2 Arrives: Industry Upheaval on the Eve of AI Margin Collapse
The rise of Zhipu's GLM 5.2 is accelerating the democratization of LLM capabilities. This article analyzes the commoditization of foundation models, the logic behind margin collapse, and the opportunities and challenges facing application-layer and foundation model firms.
Read more →
·2 min
Training Just One Transformer Layer Can Match Full-Parameter RL Training?
A controversial study shows training just one Transformer layer can match full-parameter RL training. We analyze the technical principles, engineering value, and limitations of this approach.
Read more →
·4 min
NVFP4 Quantization in Practice: A Guide to Compressing Large Models with NVIDIA Model Optimizer
Deep dive into NVFP4 quantization: using NVIDIA Model Optimizer to compress Nemotron 3 Ultra to FP4 checkpoints, reducing memory by 75% and boosting inference throughput on Blackwell GPUs.
Read more →
·5 min
NVIDIA AI-Q Blueprint × OCI: A Practical Guide to Production Deployment of Enterprise AI Agents
Deep dive into NVIDIA AI-Q Blueprint production deployment on Oracle Cloud Infrastructure, covering NIM microservices, RAG architecture, multi-agent orchestration, and OCI GPU selection for enterprise AI agents.
Read more →
·5 min
NVIDIA AI-Q Blueprint × OCI: A Practical Guide to Production Deployment of Enterprise AI Agents
Deep dive into NVIDIA AI-Q Blueprint production deployment on Oracle Cloud Infrastructure, covering NIM microservices, RAG architecture, multi-agent orchestration, and OCI GPU selection.
Read more →
·3 min
LLM Development Learning Path: From Zero to Enterprise-Level Projects
A complete LLM development learning roadmap covering prompt engineering, RAG, AI Agents, and fine-tuning — helping beginners master LangChain, LlamaIndex, and more.
Read more →
·6 min
A 284B Model Running on a MacBook: The Real Breakthrough and Barriers of Local DeepSeek Inference
Redis creator runs 284B-parameter DeepSeek model on a MacBook Pro at 26 tokens/sec using a pure C engine, asymmetric quantization, and MoE architecture.
Read more →
The True Nature of Moving Fast: Freque…
·3 min
The True Nature of Moving Fast: Frequent Contact with Reality Is a Form of Humility
"Moving fast" isn't recklessness — it's intellectual humility. This article explores the shared logic behind Agile, MVP, and AI iteration: true arrogance is believing you don't need to be tested.
Read more →
·3 min
Cursor & Claude Code Enterprise Training: AI Coding Tool Division of Labor and Practical Methodology
How can R&D teams truly leverage AI coding tools? This article breaks down Cursor vs. Claude Code division of labor, an eight-step framework, and how to build reusable AI collaboration assets.
Read more →
·4 min
LLM Job Interviews: Multi-Agent and Harness Engineering Are Now Must-Know Topics
Deep analysis of LLM job interview essentials: Multi-Agent architecture, Harness engineering, Agent Loop, sandbox isolation, and memory management with career transition tips.
Read more →
·2 min
Codex Overtakes Claude Code: A Hands-On Comparison and Selection Guide for AI Coding Tools
Hands-on comparison of Codex vs Claude Code: Codex overtakes in UI aesthetics and layout. Covers domestic models, DeepSeek free options, and price-capability analysis for AI coding tools.
Read more →
·2 min
Gemma 4 12B Released: An Open-Source Lightweight Model That Runs Locally on 16GB VRAM
Google releases Gemma 4 12B open-source model with 12B parameters that runs locally on 16GB VRAM laptops. Licensed under Apache 2.0 for commercial use, with 150M+ total Gemma downloads.
Read more →
·2 min
Nex N2 Pro In-Depth Review: How Does This Chinese Open-Source Agent Model Really Perform?
In-depth review of Nex N2 Pro, a Chinese open-source Agent model. Covers frontend code generation, Agent workflows, and benchmark comparisons, revealing gaps between official claims and independent tests.
Read more →
·3 min
Cursor Composer 2.5: The Secret Behind an Open-Source Model's Reinforcement Training to a Top-3 Coding Benchmark Ranking
Cursor built Composer 2.5 on Kimi K2 open-source model, ranking 3rd on coding benchmarks and surpassing K2.6. Deep dive into Cursor's data flywheel, product architecture, and pricing.
Read more →
·3 min
Microsoft Copilot Cowork Introduces DeepSeek: Multi-Model Architecture and Enterprise AI Agent Strategy Explained
Microsoft Copilot Cowork launches with multi-model architecture, considering DeepSeek V4 as a low-cost option. Deep dive into usage-based pricing, WebIQ search, and Microsoft's enterprise AI agent strategy.
Read more →
·2 min
GLM-5.2 Passes the Vibe Check: Open-Source Models Officially Enter the Frontier Race
Zhipu AI's GLM-5.2 passes the community vibe check, showing capabilities rivaling top closed-source models. Analysis of what this means for open-source AI.
Read more →
·3 min
Tutorial: Connecting Codex to Third-Party API Proxies for Low-Cost GPT-5.5 Access
Step-by-step tutorial on connecting GPT-5.5 to Codex via API proxy using CC Switch plugin. Complete setup in minutes with Fast mode and cost optimization tips.
Read more →