#LLM diversity
210 related articles
·2 min
Gemini 3.5 Flash-Lite: A Low-Cost, High-Throughput Powerhouse for Scaling AI
A deep dive into Google's Gemini 3.5 Flash-Lite model. Designed for high-frequency repetitive tasks like ticket sorting and data extraction, it tackles the core cost challenge of enterprise AI scaling through ultra-low pricing and high throughput.
Read more →
·3 min
Deep Dive into Inkling: The First Frontier Open-Source Multimodal LLM from the West
Thinking Machines releases Inkling, an open-source multimodal LLM with near-trillion MoE parameters, 1M token context, Apache 2.0 license. Deep dive into architecture, benchmarks, and pricing.
Read more →
·3 min
Legora's Legal AI Practice: How Vertical AI Empowers Law Firms and Corporate Legal Transformation
Explore Legora's legal vertical AI practice, covering AI model selection strategies, enterprise legal transformation challenges, and the path to deploying vertical AI in the legal industry.
Read more →
·2 min
The Rise of AI-Powered Short Dramas: How Spanish-Language Micro-Series Are Reshaping Content Production
Explore how AI empowers Spanish-language micro-drama production—from script generation and voice synthesis to multilingual distribution—and its profound impact on the global content industry.
Read more →
·2 min
Gemini Always Crashes on the 16th Turn? Error 1076 Root Cause Analysis and Workarounds
Google's Gemini consistently triggers Error 1076 on the 16th conversation turn, regardless of context size. Analysis points to a session state management defect, with three workarounds provided.
Read more →
·3 min
Apple Silicon LLM Inference Speed Benchmarks: A Complete Guide to Local Large Model Performance on Mac
In-depth analysis of Apple Silicon local LLM inference speed benchmarks covering M-series memory bandwidth, model quantization, MLX framework optimization, and Mac configuration guidance.
Read more →
·5 min
A Beginner's Guide to Prompt Engineering: From One-Off Instructions to a Systematic Methodology
A beginner's guide to prompt engineering covering the four functions of prompts, the key differences from prompt engineering, a six-step systematic workflow, and critical technical and practical limitations.
Read more →
·3 min
AI Not Performing Well? Start by Getting These Simple but Often Overlooked Things Right
When your AI system underperforms, the problem is often not the model or algorithm — it's basic work like data cleaning, prompt writing, and evaluation that hasn't been done right.
Read more →
·3 min
SlopCodeBench: Why AI Code Benchmarks Are Failing
SlopCodeBench sparks deep reflection on AI code evaluation. From benchmark contamination to pass-rate pitfalls, exploring why current benchmarks fail to measure real code quality.
Read more →
·3 min
AI Not Working Well? Start by Getting These Simple but Often Overlooked Things Right
When AI systems underperform, the problem often isn't the model or algorithm — it's that basics like data cleaning, prompt writing, and evaluation aren't done right. Learn the simple fixes that matter most.
Read more →
·3 min
Poolside Laguna Model Launch: Can Silicon Valley's Open-Source Push Catch Up to China's AI?
Poolside launches Laguna open-weight model after 18 months of silence, pitting 118B parameters against Kimi K3's 2.8 trillion. Can Silicon Valley's open-source push close the gap with Chinese AI?
Read more →
·5 min
Complete Breakdown of Core Competencies for AI Agent Engineers: From Demo to Production-Grade Systems
Deep breakdown of 4 core AI Agent engineer competencies: business decomposition, multi-Agent architecture, quantitative evaluation, and engineering delivery—bridging the gap from Demo to production.
Read more →
·5 min
The Complete Guide to AI Agent Development: A Four-Stage Progressive Roadmap
A systematic guide to AI Agent development across four stages: LLM fundamentals, ReAct paradigm, memory & tools, and multi-agent collaboration for developers.
Read more →
·3 min
Poolside Laguna Model Release: Can Silicon Valley Open Source Catch Up with Chinese AI?
Poolside releases its Laguna open-weight model after 18 months of silence, challenging Moonshot's Kimi K3 with 118B vs 2.8T parameters. Can Silicon Valley close the gap with Chinese AI?
Read more →
·3 min
MediaCrawler: Deep Dive into an Open-Source Crawler Framework Covering Seven Major Platforms
Deep analysis of MediaCrawler, a popular GitHub open-source project using Playwright browser automation for multi-platform crawling across Xiaohongshu, Douyin, Kuaishou, Bilibili, Weibo, Tieba, and Zhihu.
Read more →
·3 min
MediaCrawler: Deep Dive into an Open-Source Crawler Framework Covering Seven Major Platforms
Deep dive into the popular GitHub project MediaCrawler — a Playwright-based multi-platform crawler framework supporting data collection from Xiaohongshu, Douyin, Kuaishou, Bilibili, Weibo, Tieba, and Zhihu.
Read more →
·3 min
Automating GitHub Releases: Design and Practice of a Tag-Triggered Release Action
A ten-year open source maintainer shares how to build a universal tag-to-release GitHub Action, covering its opinionated design philosophy, dogfooding validation, and AI-assisted development.
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 →
·3 min
DeepSeek Open-Sources DeepSpec: A Full-Stack Speculative Decoding Library with 60–85% Inference Speedup
DeepSeek open-sources DeepSpec, a full-stack speculative decoding library delivering 60–85% inference speedup and up to 661% throughput gains in production. MIT license, 9 checkpoints, 9 benchmarks.
Read more →
·8 min
The Complete Guide to Agent Testing: Five Core Dimensions and Automation in Practice
An in-depth analysis of the five core dimensions of AI Agent testing: command safety, tool-calling accuracy, task planning, output consistency, and error self-repair. Master automated testing methods and the transition path for test engineers.
Read more →