#autoregressive model
445 related articles
Deep Dives·4 min
AI Hallucinations: Why Large Language Models Inevitably "Make Things Up" and How to Deal With It
Deep dive into AI hallucination's three root causes: training objective flaws, exposure bias, and probabilistic generation. Covers classification and practical mitigation strategies including RAG.
Read more →
Deep Dives·2 min
The "Worse is Better" Philosophy of Large Model Design: Why Simple and Brutal Beats Refined and Complex
Analyzing the "worse is better" philosophy in large model architecture: why DeepSeek V4 dropped N-gram, why Transformer dominates AI, and three iron laws of simple, efficient model design.
Read more →
Tech Frontiers·3 min
Claude Powers NASA Mars Rover Route Planning, Windsurf Launches IDE Model Arena
Claude plans routes for NASA's Perseverance rover, Windsurf launches Arena Mode for in-IDE model comparison, SenseTime open-sources multimodal reasoning models, and Anthropic research reveals pros and cons of AI-assisted learning.
Read more →
Tech Frontiers·3 min
Claude Powers NASA Mars Rover Route Planning, Windsurf Launches IDE Model Arena
Claude plans routes for NASA's Perseverance rover, Windsurf launches Arena Mode for in-IDE model comparison, SenseTime open-sources multimodal reasoning models, and Anthropic research reveals pros and cons of AI-assisted learning.
Read more →
Deep Dives·3 min
Complete Guide to LLM Training: Pre-training, SFT Fine-tuning, and Preference Alignment Explained
Complete guide to the three core LLM training stages: pre-training, supervised fine-tuning (SFT), and preference alignment (DPO/PPO), covering LoRA, distillation, quantization, and pruning.
Read more →
Tutorials·2 min
Harness Engineering Explained: The Role Shift from Coder to AI Supervisor
Deep dive into Harness Engineering: how engineers shift from coders to AI supervisors. Learn to solve agent drift, feedback optimization, and build future-proof engineering skills.
Read more →
Product Reviews·2 min
GPT 5.5 Image 2.0 for Academic Illustrations: Technical Roadmaps & Defense PPTs Compared with Gemini
Hands-on testing of GPT 5.5 Image 2.0 for research technical roadmaps and thesis defense PPTs, compared with Gemini Pro on quality, stability, and academic adaptability.
Read more →
Product Reviews·3 min
Moore Threads AI Coding Plan: A Fully Domestic AI Programming Service with 30-Day Free Trial
Moore Threads launches AI Coding Plan powered by its MTT S5000 GPU and GLM-4 code model, achieving full-stack domestic AI coding. Compatible with VS Code and Cursor, with a 30-day free trial.
Read more →
Tutorials·3 min
llama.cpp MTP Acceleration Deployment Guide: Configuration Steps & Real-World Benchmarks
Guide to enabling MTP multi-Token prediction acceleration in llama.cpp, covering CUDA setup, desktop configuration, model selection, and benchmarks showing ~60 Token/s with Qwen3 27B.
Read more →
Tutorials·3 min
Practical Guide to Building an Intelligent Coding Assistant with the OpenAI API
A detailed guide on building an intelligent code assistant with the OpenAI API, covering Chat Completions, Responses, and Assistants APIs, GPT-4.5 vs Codex models, and tools like Function Calling and Code Interpreter.
Read more →
Deep Dives·3 min
DeepSeek V4 Deep Technical Breakdown: Million-Token Context and Extreme Cost Efficiency
Deep analysis of DeepSeek V4's core architecture: Hybrid Compressed Attention, Manifold-Constrained Hyperconnection, and MUON optimizer—how they cut inference costs by 10x and enable million-token context processing.
Read more →
Deep Dives·4 min
Core Principles of the Transformer Architecture: A Deep Dive into Self-Attention Mechanisms and Engineering Optimizations
Deep dive into Transformer architecture covering self-attention QKV mechanics, Encoder-Decoder structure, Flash Attention memory optimization, RoPE positional encoding, and GQA inference acceleration.
Read more →
Tutorials·4 min
Getting Started with Codex from Scratch: Why It's a Better Fit Than Claude Code for Most People
In-depth comparison of OpenAI Codex vs Claude Code covering account stability, usage quotas, browser control, and automation — helping you get started with this all-in-one AI Agent desktop tool.
Read more →
Industry Insights·4 min
Google I/O 2026 Deep Dive: From Super Apps to the Battle for Ecosystem Dominance
Deep analysis of Google I/O 2026: Gemini 3.5 Flash, Omni video tools, Spark personal Agent, and how Google, OpenAI, and Anthropic are competing for AI ecosystem dominance.
Read more →
Tutorials·3 min
oMLX + MTP + Qwen3.6: Local AI Coding Speed Breaks New Records
Using oMLX with MTP and Qwen3.6 35B on Apple Silicon Mac to achieve 86.7 tokens/s local coding speed, building a full-stack app in under 5 minutes.
Read more →
Industry Insights·2 min
AMD MI355X Beats B200: Full-Stack Optimization Breakdown for 5% Lower TCO on DeepSeek-R1 Inference
AMD Instinct MI355X achieves 5% lower TCO than NVIDIA B200 on DeepSeek-R1 disaggregated inference via SGLang+MoRI full-stack optimization with 1.25x per-GPU throughput.
Read more →
Tech Frontiers·1 min
Cloudflare Contributes Critical KV Cache and Mooncake Fixes to SGLang
Cloudflare contributes decode KV cache offload and Mooncake recovery fixes to SGLang, resolving garbled output under high concurrency for Kimi K2.6 and enabling automatic fault recovery in distributed inference.
Read more →
Product Reviews·2 min
API Aggregation Proxy Platforms Tested: One Interface to Call 100+ AI Models
Hands-on testing of an API aggregation proxy platform's model calling capabilities, including GPT-Image2 image generation, cost analysis, and coverage of 100+ models like Claude and Gemini.
Read more →
Product Reviews·2 min
Claude Opus 4.8 Deep Dive: A Comprehensive Review of Judgment, Honesty, and Cost-Effectiveness
Deep dive into Claude Opus 4.8's core upgrades: improved judgment, optimized honest feedback, and Fast Mode costs cut to one-third. Compared with DeepSeek and GPT-5.5 for AI coding and long-context reasoning.
Read more →
Tech Frontiers·3 min
June AI Showdown: Mythos, Sonnet 4.8, and GPT-5.6 All Revealed
June 2025 becomes AI's densest release month: Anthropic Mythos nears launch, Claude Sonnet/Opus 4.8 skip-level upgrades, GPT-5.6 rapid iteration, DeepSeek V4 Pro permanent 75% price cut.
Read more →