#Group Relative Policy Optimization
85 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 →
·6 min
What Is an FDE? Decoding the Most Sought-After Hybrid Engineer in the AI Deployment Era
FDE (Forward Deployed Engineer) is the hottest emerging role in the AI deployment wave, combining a technical CTO, full-stack AI engineer, and business consultant. Learn the two FDE tracks, core skills, and how to transition into one.
Read more →
·4 min
FTPO: A Training-Level Solution to AI Repetition Loops
FTPO (Final Token Preference Optimization) tackles AI "Doom Loops" at the training level rather than patching them at inference time — exploring its principles, value for small/quantized models, and open challenges.
Read more →
·5 min
Davit: A Native GUI Management Tool Built Specifically for Apple Containers
Davit is an open-source native macOS UI tool built for Apple Containers, offering graphical container status management, image viewing, and log monitoring.
Read more →
·6 min
Unsloth Major Update: DeepSeek-V4 Support and a Deep Dive into NVFP4 Quantized Export
Unsloth v0.1.481-beta adds full DeepSeek-V4-Flash support, NVFP4/FP8/imatrix GGUF quantized export, 1.3x faster GRPO, 3-5x faster MoE training, and an OpenAI-compatible API service in Studio.
Read more →
·6 min
Complete Guide to Deploying Dify Locally: Docker + Ollama + RAG Setup Tutorial
A detailed guide to deploying the Dify agent platform locally: from Docker setup and integrating Ollama + DeepSeek local LLMs to workflow orchestration and RAG knowledge base construction.
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 →
·7 min
Why Does WhatsApp Drain So Much Battery? A Deep Dive into the Technical Causes and a Power-Saving Guide
An in-depth analysis of the core technical reasons behind WhatsApp's battery drain—covering persistent connection heartbeats, background tasks, media processing, E2E encryption, and iOS/Android differences—plus 4 practical power-saving tips.
Read more →
·7 min
Amble Electric Buggy: A New Leisure Mobility Option Built for the 'Second Car'
Portuguese startup Amble launches an electric buggy positioned as a 'second car,' entering the leisure mobility market with boxy design and minimalist philosophy—no autonomous driving, no range race.
Read more →
·7 min
The Revenge of the Philosophy Majors in the AI Era: Why Critical Thinking Has Become the New Scarce Resource
As generative AI sweeps the workplace, once-marginalized philosophy and humanities are being revalued. This article explores why critical thinking, ethical judgment, and questioning are the new scarce competencies in the AI era.
Read more →
·5 min
Major Unsloth Update: NVFP4 Quantization Export and DeepSeek-V4 Training Support
Unsloth v0.1.48-beta released, adding NVFP4/FP8 quantization export, OpenAI-compatible API hot-swapping, 3-5x faster MoE training, and 1.3x faster GRPO, covering the full LLM fine-tuning, quantization, and local deployment pipeline.
Read more →
·7 min
GPT-5.6 Sol vs. Fable 5: Can Half the Price Match the Flagship?
OpenAI launches GPT-5.6 Sol at half the price of Anthropic's Fable 5. We compare both models on HealthBench, cybersecurity and more using hard system-card data, analyzing Sol's cost-effectiveness and shifts in AI power.
Read more →
·6 min
Fable 5 vs GPT-5.6 Sol: Cost-Efficiency Redefines the Frontier AI Landscape
An in-depth analysis of the head-to-head between Anthropic's Fable 5 and OpenAI's GPT-5.6 Sol: the performance gap, the logic behind pricing strategies, and the concentration-of-power concerns raised by U.S. government involvement.
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 →
·6 min
Benchmarking as Data Activation: Giving Domain Data a Direction to Climb
How benchmarking transforms dormant domain data into an AI optimization engine. From healthcare to law to manufacturing, building vertical benchmarks activates proprietary data and builds a strategic moat.
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 →
·7 min
Dispersion Loss: A Key Technique for Solving Embedding Condensation in Small Language Models
Embedding condensation is a hidden bottleneck in small language model training. Dispersion Loss combats this by enforcing representation spread during training at zero inference cost.
Read more →
·7 min
Claude Code Command Orchestration: One-Click Content Research and Auto-Publishing
Learn how to orchestrate Claude Code custom commands to chain content research and social media publishing agents into a fully automated workflow with one command.
Read more →
·6 min
Anthropic Launches Life Sciences Hackathon with $100K to Empower AI-Driven Research
Anthropic launches a global life sciences hackathon with Gladstone Institutes, offering $100K in API credits to advance AI-driven scientific research using Claude Science and Claude Code.
Read more →
·7 min
AI Agent Practical Guide: From Content Generation to Enterprise Applications
A deep dive into AI Agent's two core directions: 2C content generation (text/images/video) and 2B enterprise applications (RAG/AutoGen/LLM integration). With real startup cases and practical methods.
Read more →