#Function Calling replacement
157 related articles
·3 min
Gemini 2.5 Flash Deprecation: A Practical Migration Guide for Image Understanding Models
Gemini 2.5 Flash will be deprecated in October 2026. Learn how to choose between gemini-3.1-flash-lite and gemini-3.5-flash-lite for image understanding tasks with migration evaluation methods and architecture tips.
Read more →
·2 min
Older Google Home Gets Gemini Live Upgrade: Conditions and Experience Fully Explained
Google is rolling out Gemini Live conversational AI to older Google Home speakers, but subscription or plan requirements may apply. Here's what you need to know.
Read more →
·2 min
Older Google Home Gets Gemini Live Upgrade: Complete Breakdown of Requirements and Experience
Google is rolling out Gemini Live conversational AI to older Google Home speakers, but subscription or plan restrictions may apply. Full breakdown of the upgrade details and impact.
Read more →
·4 min
Statistical Foundations of Machine Learning: From MLE to EWMA and Deep Learning Optimizer Principles
Deep analysis of core ML statistics concepts covering MLE derivation, multivariate Gaussian, linear regression and least squares equivalence, empirical risk minimization, method of moments, and EWMA's connection to Adam optimizer.
Read more →
·5 min
Opus 5 Builds a No Man's Sky-Style Exploration Game in One Day: MCP and Sub-Agent Architecture Explained
A developer used Anthropic's Opus 5 model to build a No Man's Sky-style space exploration game in one day using Blender MCP and sub-agents. Deep dive into the technical architecture and industry implications.
Read more →
·4 min
LangChain Guardrails Explained: Building Safe and Controllable AI Agents
A detailed guide to LangChain Guardrails covering layered ecosystem architecture, middleware implementation, deterministic and model-driven protection for building production-grade secure AI Agents.
Read more →
·2 min
Chrome Built-in AI Explained: How Locally Running Models Protect Your Privacy
Explore Chrome Built-in AI technology and how running AI models locally in the browser enables zero data upload, instant responses, and stronger privacy protection.
Read more →
·2 min
Chrome Built-in AI Explained: How Locally Running Models Protect Your Privacy
Deep dive into Chrome Built-in AI technology, exploring how running AI models locally in the browser achieves zero data uploads, instant responses, and stronger privacy protection.
Read more →
·3 min
Carta: Pandoc Rewritten in Rust — 45x Faster, 20x Smaller
Carta is a Rust reimplementation of Pandoc that produces a 9MB binary (1/20th of Pandoc) and achieves up to 45x faster conversion speeds for Markdown, DOCX, LaTeX, and more.
Read more →
·3 min
GitHub Agentic Workflows in Practice: Automating Cross-Repository Documentation Updates
Learn how GitHub Agentic Workflows automate cross-repo documentation updates. See the Aspire team's AI-driven approach: event triggers, smart drafting, and SME review to keep docs in sync with code.
Read more →
·3 min
Sebastian Lague's Custom Graphics Library: A Complete Breakdown of Building a Renderer from Scratch
Deep dive into Sebastian Lague's experiment building a graphics library from scratch, covering rasterization, depth buffering, texture mapping, and the educational value of software renderers.
Read more →
·3 min
AI-Assisted GeeTest Four-Image CAPTCHA Reverse Engineering: A Complete Efficiency Guide
A complete walkthrough of AI-assisted GeeTest four-image CAPTCHA reverse engineering: from capturing the w parameter to AI analyzing obfuscated code and generating runnable scripts in minutes.
Read more →
·7 min
Harness Engineering: Why a Powerful Model Isn't Enough — Here's What Really Matters
A data-deletion disaster reveals the biggest AI Agent risk: the problem isn't the model, it's Harness design. Learn context management, process standards, and permission isolation.
Read more →
·2 min
FastAPI Fundamentals: Frontend-Backend Separation and RESTful Design Explained
Learn the core concepts behind FastAPI: frontend-backend separation, API interface design, and RESTful specification. Master resource-oriented design before writing your first line of code.
Read more →
·6 min
The Evolution of Claude Code: From Manual Review to 65% Fully-Automated PRs
Anthropic engineers reveal Claude Code's 18-month evolution: system prompt cut by 80%, 65% of PRs shipped automatically by AI, Claude Tag collaboration, and the safety logic behind auto mode.
Read more →
AstrBot: A Deep Dive into the Multi-Pl…
·2 min
AstrBot: A Deep Dive into the Multi-Platform AI Agent Development Framework
AstrBot is an open-source AI Agent framework supporting WeChat, QQ, Telegram and more, with multi-LLM compatibility and plugin extensibility. Full technical breakdown inside.
Read more →
·4 min
Cross-Platform AI Agent Setup Guide: Breaking Free from Vendor Lock-In for Good
Model performance gaps are closing. Real competitive advantage lies in portable AI agent architecture. Learn how to build a workspace that works across Claude Code, Codex, and beyond — no vendor lock-in.
Read more →
·3 min
Zero-Code AI Financial Mini Program: A Complete Non-Programmer's Guide
Can't code? Learn how to build a WeChat Mini Program financial management system from scratch using AI coding tool Codex — covering tool selection, OCR invoicing, iteration, and publishing.
Read more →
Agentty: An 11MB Lightweight Claude Co…
·2 min
Agentty: An 11MB Lightweight Claude Code Alternative Built with C++26
Agentty is an open-source AI coding assistant written in C++26, compiling to just 11MB. Positioned as a drop-in alternative to Claude Code, it explores lightweight, native-first AI tooling.
Read more →
DCG: A Rust-Powered Safety Guard That …
·2 min
DCG: A Rust-Powered Safety Guard That Intercepts Dangerous AI Agent Commands
DCG is an open-source Rust tool that intercepts dangerous shell and git commands for AI agents like Claude Code and Cursor, enabling zero-trust execution environments.
Read more →