#LLM repetition
77 related articles
·2 min
From Medieval Grimoires to AI: Humanity's Thousand-Year Quest for Instant Knowledge
From the medieval grimoire Ars Notoria to ChatGPT, humanity's desire for instant knowledge spans a millennium. Exploring the striking parallels between AI and ancient magic books, and the hidden costs of instant knowledge.
Read more →
·5 min
MemBoostAI: A Deep Dive into the AI-Powered Daily Memory Training Tool
MemBoostAI is a memory training app combining cognitive science with AI. Through short daily practice, active recall, and gamified challenges, it helps users boost memory retention. A deep analysis of its features, science, and differences from traditional flashcard tools.
Read more →
·3 min
BrainFeed: Turning Mindless Scrolling into Learning with an AI-Powered Personalized Knowledge Feed
BrainFeed is an AI-powered personalized learning feed that turns articles and videos into swipeable knowledge cards with spaced repetition, transforming mindless scrolling into effective learning.
Read more →
·5 min
Loop Engineering Explained: The New Programming Paradigm Where AI Prompts Itself
Loop Engineering is a paradigm shift in AI usage. Learn how to build automated loops where agents explore, execute, and verify tasks autonomously, with a hands-on e-commerce case study.
Read more →
·2 min
The Complete Methodology for Landing an Offer Using Claude for Mock Interviews
A job seeker used Claude for AI mock interviews, fixing rambling answers and buried examples through iterative feedback, and landed the offer. Full methodology inside.
Read more →
·5 min
Ollama Performance Degrades After Connecting to OpenWebUI? A Complete Troubleshooting Guide
Complete guide to troubleshooting Ollama performance degradation with OpenWebUI, covering num_ctx truncation, sampling parameter differences, GPU resource contention, and system prompt interference.
Read more →
·2 min
Multi-Agent Collaborative Paper Writing System: End-to-End Automation with FastAPI + Vue 3
An in-depth look at an intelligent paper writing platform built on FastAPI + Vue 3, combining LLM, RAG, and multi-Agent collaboration for full-process automation—an excellent case study for AI developers.
Read more →
·2 min
Testing Fan Browser Agent: Auto-Filling a Korean Visa Application End-to-End
A developer tests Fan Browser Agent on a real Korean visa application: autonomous flow planning, filling 30+ form fields automatically, and handling upload errors.
Read more →
·4 min
Vibe Coding for Beginners: 4 Pitfalls Every Non-Coder Must Avoid
New to Vibe Coding? Avoid these 4 beginner traps: unclear AI boundaries, oversized goals, wrong role mindset, and C drive overflow. Real tips for non-coders.
Read more →
·2 min
Open-Source Multi-Platform Auto-Publishing Skill: How AI Is Freeing Content Creators from Repetitive Busywork
A Bilibili creator open-sourced a Codex-based multi-platform auto-publishing Skill with 95% stability. It auto-fills titles, tags, and thumbnails on Bilibili, Douyin, and more, then waits for user confirmation before publishing.
Read more →
·3 min
AI Video Editing in Practice: How to Compress 5 Hours of Rough Cuts Down to 30 Minutes
A deep dive comparing ChatCat and VSCALE AI editing tools, showing how rough cuts shrink from 5 hours to 30 minutes — covering multi-cam sync, lossless DaVinci import, and AI's real limits.
Read more →
·3 min
How CS Students Should Use AI to Learn Programming — Without the "Used It But Learned Nothing" Trap
Many CS students use AI to learn programming but later feel they didn't truly learn. This article breaks down the two AI learning traps and offers Socratic questioning, the Feynman Technique, and more to turn AI into a real learning accelerator.
Read more →
·3 min
Does AI Have Consciousness? A Deep Philosophical Conversation with ChatGPT's Voice Model
Can AI be conscious? Exploring GPT-4o voice model technology and philosophy — the Problem of Other Minds, Descartes, and what makes consciousness real.
Read more →
·2 min
Running Qwen 122B on 8GB VRAM: A Complete Guide to Quantized Local Deployment
A Bilibili creator ran Qwen 122B with 256K context on just 8GB VRAM + 64GB RAM using llama.cpp. Full breakdown of quantization, deployment params, performance, and cost-effective alternatives.
Read more →
ContextVault: Building a Shared Memory…
·2 min
ContextVault: Building a Shared Memory Layer for Team AI Collaboration
ContextVault builds a shared memory layer for team AI collaboration, tackling fragmented AI context and knowledge silos. Explore its technical positioning, use cases, and challenges in context engineering.
Read more →
·4 min
Agent Loop in Practice: A Guide to Building Self-Improving Automation with Guardrails
A deep dive into building verifiable, self-evolving Agent automation loops with Claude Code and Codex — covering Loop Contracts, four trigger types, three-phase execution architecture, and Evolve Loops.
Read more →
Turning Papers into Interactive Course…
·2 min
Turning Papers into Interactive Courses with AI: An Experiment in LLM-Powered Self-Learning
An indie developer turned the Flash Attention paper into a Brilliant-style interactive course using AI. A deep dive into how LLMs can fill long-tail learning gaps.
Read more →
·2 min
15-Year-Old Trains 200M MoE Language Model from Scratch: Full Architecture & Hands-On Breakdown
A 15-year-old trained Tiny-MoE, a 200M-parameter MoE language model from scratch using free Kaggle GPUs, featuring MLA attention, RoPE+YaRN, and native PyTorch.
Read more →
·4 min
From Enter to First Token: Decrypting the Full LLM Inference Pipeline (Autoregression, KV Cache & Decoding Strategies)
From pressing Enter to the first character appearing, what happens inside an LLM? This article breaks down autoregressive generation, KV cache acceleration, and decoding strategies like temperature, Top-k, and Top-p.
Read more →
·5 min
Maximizing Codex Weekly Quota: A Complete Guide to Goal Commands and Long-Running Agent Configuration
Master Codex's Goal command mechanism. Use five standard project settings—agents.md, context.md, active-context and more—to solve context forgetting and hallucination in long-running Agents and maximize your weekly quota.
Read more →