Learn and create, pioneering the AI era.
This article addresses frequent Kimi API queries, explains the API's purpose, available endpoints, model specifications, token‑based pricing, differences from the web assistant, response variability, JSON output workarounds, and shares upcoming roadmap items for developers building AI applications.
The author tests Moonshot’s Kimi API, revealing its 200 k‑character context window, superior token‑to‑character ratio compared with GPT‑3.5 and Gemini, and performance that, while slower than GPT‑3.5 Turbo, rivals GPT‑4 Turbo, all while offering OpenAI‑compatible endpoints and free credit for developers.
The article walks through OpenAI’s own admission of Sora’s shortcomings—such as unrealistic physics, misplaced spatial details, and erratic object behavior—by showcasing concrete demo failures, additional observations, and technical notes about its diffusion‑based, transformer architecture and metadata embedding.
This article walks through the ChatGPT interface for creating custom GPTs, explains configuring basic information, details the five built‑in tools—knowledge base, web browsing, DALL·E image generation, code interpreter, and external API actions—and demonstrates each with concrete prompts and screenshots.
Learn how to protect your custom GPT from prompt‑injection attacks that expose its system prompt and follow the step‑by‑step process to publish it on the GPTs Store, including selecting visibility, completing developer verification via payment or domain, and choosing a category.
This article explains what GPTs (customized ChatGPTs) are, outlines the subscription and access requirements, walks through the GPTs store interface, and demonstrates creating a logo with the “Logo Creator” GPT, highlighting the multi‑turn workflow and built‑in DALL·E 3 generation.
This article walks you through five progressive levels—from basic usage to prompt engineering, custom instructions, bespoke Prompt bots, and finally creating OpenAI GPTs—demonstrating how structured prompts, role setting, output formatting, and integrated extensions can dramatically boost ChatGPT’s effectiveness for professional tasks.
The article examines whether creators can claim copyright over AI‑generated works by analyzing two Chinese court cases, the role of user agreements on platforms like Baidu Wenxin Yige and Midjourney, and the impact of training‑data disputes.
With the upcoming GPTs Store opening, developers must guard against system‑prompt leaks and knowledge‑base theft by understanding the disclosed vulnerabilities and applying the recommended protective prompts and sandbox restrictions.
The article walks through the author's investigation of why a Node.js CLI tool using Got fails to route HTTPS requests through Charles, compares direct proxy versus reverse‑proxy strategies, and provides a step‑by‑step implementation using https‑proxy‑agent and Got with certificate verification disabled, enabling successful request capture.
