This article explains what ChatGPT is, how it builds on natural-language-processing and the Transformer-based GPT series, details its model-size growth, architectural enhancements, multilingual support, and walks through the tokenization-to-generation pipeline that enables coherent AI-driven conversations.
This tutorial shows how to quickly integrate ChatGPT and Stable Diffusion AIGC models into a WeChat public account or mini‑program using the AIGCaaS platform, covering registration, API Explorer usage, code customization, asynchronous handling, and deployment with Python Flask.
The article outlines how ChatGPT 4.0 can significantly improve product managers' workflow across research, planning, design, project execution, and iteration by providing prompt engineering techniques, practical examples, and actionable recommendations while emphasizing security and information‑risk considerations.
ChatGPT’s web interface has been increasingly showing “Something went wrong” errors after idle periods, and this guide explains two remedies: using an OpenAI API key for more stable access, and installing the KeepChatGPT Chrome/Tampermonkey extension, which suppresses the error and adds several usability enhancements.
This article explains how ChatGPT works by covering the fundamentals of natural language processing, generative language models, deep learning, the Transformer architecture, attention mechanisms, few‑shot learning, and the reinforcement‑learning techniques that align its outputs with human preferences.
This article compiles a wide range of practical ChatGPT applications—including grammar correction, translation, code explanation, error fixing, creative generation, and more—illustrated with descriptions, code snippets, and images to help users explore the model's versatile capabilities.
The article explains how ChatGPT’s surprising step‑by‑step reasoning, known as Chain of Thought, emerged as a technical breakthrough, links it to model scaling, cognitive System 1/2 theory, and the influence of code data in training large language models.
This article translates Ibrahim John’s book on prompt engineering for ChatGPT, explaining a wide range of prompting techniques—including instruction, role, seed‑word, zero‑shot, few‑shot, and reinforcement‑learning prompts—through clear English descriptions, formulas, and illustrative examples to help readers obtain high‑quality model outputs.
This guide shows front‑end developers how to generate realistic mock data with ChatGPT, export it as JSON, and instantly serve a full RESTful mock API using json‑server, covering schema design, routing, filtering, pagination, sorting, and query operators.
A study by Quebec researchers shows that ChatGPT often produces insecure code across C, C++, Python, and Java, warns that the model rarely flags these issues unless explicitly asked, and highlights ethical inconsistencies in its handling of vulnerable code.
The article traces the evolution from Turing's seminal AI test through the rise of ChatGPT, explains how large language models rely on knowledge graphs built from massive unstructured data, and examines the challenges and advantages of modern graph databases for high‑performance, flexible, and explainable AI applications.
The article traces the evolution from Turing's seminal AI test through ChatGPT's massive adoption, explains how large language models rely on knowledge graphs built via graph databases, and highlights the technical challenges and advantages of high‑performance, flexible, low‑code graph database solutions for real‑time AI applications.
The article explains why ChatGPT’s “Something went wrong” error appears frequently, compares using an OpenAI API key versus installing the KeepChatGPT Chrome extension, and provides a step‑by‑step guide to install Tampermonkey and the extension to permanently stop the error.
This guide walks you through preparing an OpenAI account, obtaining an API key, using the Completion endpoint with example JSON, calling the API from plain JavaScript/HTML, and integrating the same service into a Spring Boot application with Maven dependencies and Java code.
This article explains how to use Server‑Sent Events (SSE) and the EventSource API to stream ChatGPT responses in real time, covering both browser‑side JavaScript examples and Node.js backend proxy code, along with configuration tips for Nginx and compatibility notes.
At a live demo, OpenAI co‑founder Greg Brockman revealed ChatGPT’s upcoming Plugins, Browsing, and Code Interpreter features that let the model generate images, add items to a shopping cart, post to Twitter, fact‑check answers, and automatically analyze large datasets, illustrating a true AutoGPT experience.
OpenAI's CEO declares that the development strategy behind ChatGPT has concluded, urging the AI community to explore new directions beyond ever‑larger models as GPT‑4 reaches the limits of scaling and cost effectiveness.
This extensive report examines ChatGPT’s origins, the evolution of artificial intelligence and natural language processing, details the underlying Transformer architecture and GPT series, discusses its limitations, and explores the wide-ranging commercial applications and future prospects of generative AI.
This study investigates the capability of ChatGPT, a large language model, to detect common smart‑contract vulnerabilities, evaluates its performance against traditional tools across multiple datasets, and discusses its strengths, limitations, and future potential in blockchain security auditing.
This article outlines four practical QA scenarios—building a simple API automation framework, creating a Locust performance‑testing demo, writing functional test cases, and analyzing product requirements for hidden risks—while emphasizing how mastering ChatGPT can boost a tester's competitiveness.
Chinese tech giants including Baidu, Tencent, Alibaba, ByteDance, Huawei, NetEase, and 360 have launched or are developing their own ChatGPT-like large language model products, detailing release dates, technical specifications, applications, and the challenges faced in the domestic AI landscape.
The article examines how ChatGPT can generate test cases, automate scripts, and assist in various AI‑driven tasks while arguing that human testers remain indispensable for nuanced judgment, risk management, and continuous learning in the evolving software testing landscape.
DeepSpeed Chat provides a fast, affordable, and scalable system for end‑to‑end RLHF training of ChatGPT‑style large language models, offering one‑click scripts, detailed performance benchmarks across GPU configurations, support for many model families, and a flexible API for custom RLHF pipelines.
In this talk, Wu Jun explains the decades‑long evolution of language models, why ChatGPT sparked hype yet isn’t a breakthrough, how massive compute and data power it, and what practical effects it has on creators, energy use, and the tech industry.
Cursor is a free, open‑source AI coding editor built on ChatGPT‑3 that supports multiple languages, offers features like code generation, diff comparison, chat‑style assistance, lint fixing, and aims to become a highly efficient development environment through future AI‑driven enhancements.
In a live talk, AI veteran Wu Jun explains why the hype around ChatGPT is overblown, traces the history of language models from the 1970s, details the massive compute and data requirements, and discusses the real impact of large‑scale AI on society and work.
The article surveys major large language models—including GPT‑3, T5, LaMDA, Jurassic‑1, MT‑NLG, Gopher, Chinchilla, PaLM, U‑PaLM, OPT, LLaMA, BLOOM, GLM‑130B, and ERNIE 3.0 Titan—explains their architectures, scaling trade‑offs, and then details instruction‑fine‑tuned variants such as T0, FLAN, GPT‑3.5, ChatGPT, GPT‑4, Alpaca and ChatGLM, providing references for further study.
This article shows how to use ChatGPT to conduct statistical significance testing for A/B experiments, explains the underlying concepts of Type I and Type II errors, demonstrates a practical “spell” for conversion data, and provides a reliable online calculator for quick results.
Microsoft open‑sourced DeepSpeed‑Chat, a toolkit that streamlines the end‑to‑end training and inference of ChatGPT‑like large language models using RLHF, delivering up to fifteen‑fold speedups and dramatically lower costs, even on a single GPU.
Developer Yeo Kheng Meng created doschgpt, a ChatGPT client that runs on a 1984 IBM 5155 MS‑DOS machine by using Open Watcom, a Packet Driver, manual HTTP POST construction, and a Go HTTPS proxy to bridge modern OpenAI services.
A recent OpenAI investigation revealed that a bug in the redis-py client caused ChatGPT to leak conversation histories and personal details of about 1.2% of Plus users, prompting a temporary service shutdown and a rapid patch deployment.
The article shows how developers can transform ChatGPT from a simple Q&A bot into a powerful productivity assistant by mastering prompt engineering and applying it to tasks such as technical document summarization, task decomposition, code reading, optimization, generation, unit‑test creation, and plugin integration, thereby augmenting their workflow.
This article provides a comprehensive overview of ChatGPT prompt engineering, covering its background, design principles, step‑by‑step workflow, numerous practical examples—including code generation, entity extraction, and style rewriting—and discusses why prompts are crucial for large language model performance.
This article introduces ColossalChat, an open‑source ChatGPT‑like model built on LLaMA and the Colossal‑AI framework, detailing its full RLHF workflow, bilingual dataset, low‑cost training tricks, quantized inference, and step‑by‑step code to help developers quickly replicate large‑language‑model capabilities.
In this talk, AI expert Wu Jun explains why ChatGPT has caused widespread fear, traces the historical development of language models from the 1970s to today, clarifies the massive computational and data requirements, and discusses the real impact and opportunities of large‑scale AI systems.
This article examines how ChatGPT can assist various stages of user research—search, summarisation, content polishing, and interview simulation—highlighting its potential to reduce costs and increase efficiency while also noting its current limitations and the need for critical validation.
This study systematically evaluates ChatGPT and other large language models on their ability to answer commonsense questions, assess their knowledge awareness, and utilize generated knowledge for reasoning, revealing strong QA performance but notable gaps in social and temporal commonsense and in leveraging contextual knowledge.
The author shares a personal journey of using ChatGPT as a knowledge engine, illustrating six key benefits—answering complex questions, applying Occam's razor, simplifying concepts for beginners, enabling generative learning, fostering T‑shaped expertise, and mastering effective prompting—through concrete examples ranging from metadata explanations to Docker deployment steps.
In a SETalk livestream, experts discuss how ChatGPT and Copilot X dramatically boost coding efficiency, lower entry barriers, reshape software development workflows, raise concerns about job displacement, and outline three emerging paradigms—LLM for SE, SE for LLM, and LLM as SE—while highlighting current limitations and future trends.
The article explains that ChatGPT produces responses by converting words into high‑dimensional vectors, feeding them through neural networks, and selecting tokens based on probability distributions, while also contrasting GPT with BERT and describing a related training event.
This article explains what ChatGPT is, how it works, its main use cases, and provides a detailed, code‑free tutorial for registering, obtaining an API token, forking the source code, and deploying a fully functional ChatGPT instance on Railway with custom domain support.
This article walks through creating a GitLab code‑review bot that leverages the ChatGPT API, detailing request handling with Axios, constructing prompts, interacting with both ChatGPT and GitLab APIs, and posting automated review comments back to merge requests.
This article explores how ChatGPT’s remarkable abilities stem from the Transformer architecture, reinforcement learning from human feedback, and the insights presented in the fourth edition of "Artificial Intelligence: A Modern Approach," highlighting key AI milestones and technical foundations.
This article highlights six recent open‑source projects on GitHub—including Microsoft’s Semantic‑Kernel SDK, Shell GPT command‑line tool, Feishu GPT productivity bot, Bloop code‑search engine, a GPT‑4 PDF chatbot, and a VSCode ChatGPT extension—showcasing practical AI applications for developers.
The article analyses how foundation models like ChatGPT are reshaping software engineering, highlighting their impressive capabilities for small‑scale tasks, the challenges they face with large, complex systems, the importance of digitalizing development knowledge, and proposes an intelligent interaction engine to combine human expertise with AI tools.
A wave of unexpected ChatGPT account bans has sparked panic across social platforms, with users reporting locked accounts, halted registrations, and malfunctioning Plus subscriptions, while speculation ranges from mass‑registration sweeps to API misuse, prompting advice on detection and appeal procedures.
This guide shows how to prompt ChatGPT as a Java developer, transform a flawed if‑else calculator into a clean Strategy‑pattern implementation, and write comprehensive JUnit tests, while warning about code‑security risks when using large language models.
The article examines how ChatGPT automates many manual tasks, reducing demand for translators, editors, customer support reps, and data analysts, while boosting opportunities for chatbot developers, NLP engineers, data scientists, content creators, and software developers, and outlines broader industry advancements driven by AI.
This article investigates the translation quality of Deepl and ChatGPT for the game 'Naraka: Bladepoint' by comparing their outputs against professional human translations across Chinese‑English, Chinese‑Spanish, and English‑Spanish pairs using BLEU scores and manual assessment, revealing strengths and limitations of each system.
The article examines ChatGPT’s underlying software architecture, detailing its cloud deployment on AWS and Azure, database choices like PostgreSQL and Redis, front‑end technologies such as TypeScript and React, core AI frameworks including PyTorch and Triton, as well as its container orchestration, monitoring, and programming language ecosystem.
This article recounts a developer's hands‑on experiment using ChatGPT to generate Flutter code for drawing a yellow five‑pointed star, iteratively refining the design, adding explosion particle animation, and reflecting on the strengths and quirks of in‑context learning AI.
This article shares a concise 10‑line Bash script, generated by ChatGPT, that captures MySQL QPS, TPS, and connection counts, timestamps each record, and appends the metrics to a log file for easy performance monitoring.
A recent Redis‑py library vulnerability caused ChatGPT to expose personal data of about 1.2% of Plus users, prompting an OpenAI apology, a detailed post‑mortem, and a series of backend and security fixes to prevent similar incidents.
A recent bug in the open‑source redis‑py library caused ChatGPT to leak personal data of about 1.2 % of Plus users, allowing some users to see others' names, emails, and partial credit‑card details; OpenAI issued an apology, published a post‑mortem, and deployed a patch to fix the Redis Cluster async client issue.
The article introduces OpenAI's newly released ChatGPT and Whisper APIs, explains their reduced costs, outlines usage details and model versions, and provides Python code examples for integrating these powerful conversational and speech‑to‑text models into third‑party applications.
Last Monday, a Redis client bug caused ChatGPT to leak user conversation histories and personal details of about 1.2% of Plus subscribers, prompting OpenAI to temporarily shut down the service, investigate, and release a patch fixing the underlying Redis‑py issue.
This article explains how ChatGPT, the popular AI chatbot, can boost developer productivity through testing, debugging, documentation, error detection, code completion, formatting, refactoring, search assistance, text classification, and summarization, while also highlighting its need for human oversight and risks such as plagiarism.
OpenAI has unveiled a suite of ChatGPT plugins—including a web‑browser, a code interpreter, a retrieval tool, and support for third‑party services—enabling the model to access up‑to‑date information, run Python code, query vector databases, and integrate external APIs, dramatically expanding its practical capabilities.
This article examines how ChatGPT’s rapid advances in natural‑language processing spark fears of job loss among developers, explains why many routine coding tasks are vulnerable, and highlights why programmers’ creative problem‑solving, debugging, and system design keep their roles secure while offering productivity benefits.
A recent OpenAI study estimates that roughly 80% of U.S. workers will see at least 10% of their tasks affected by ChatGPT and similar large language models, with about 19% of occupations potentially losing half of their tasks, highlighting widespread economic implications across all wage levels.
OpenAI has launched a ChatGPT plugin system that lets the model safely call external APIs, browse the web, and run code, enabling real‑time information retrieval, automated actions like booking travel, and powerful data analysis through official Browsing and Code Interpreter plugins.
OpenAI announced a safety‑focused ChatGPT plugin system that connects the model to third‑party APIs for real‑time information retrieval, knowledge‑base access, and task execution, showcasing first‑party browser and code‑interpreter plugins, third‑party extensions, an open‑source retrieval plugin, and a detailed debate on security implications.
This guide walks you through creating a personal ChatGPT chatbot by first setting up an OpenAI account and API key, then demonstrating how to call the completions endpoint using plain JavaScript and HTML, followed by integrating the same API into a Spring Boot application with the official Java client library, including all necessary code snippets and configuration steps.
This article provides a comprehensive technical analysis of ChatGPT, covering its cognitive model, model‑as‑a‑service architecture, front‑end integration, internal structure, API design, engineering challenges, risk‑aware AGI development, and future outlook for AI‑driven software engineering.
The article examines ChatGPT's rapid adoption, the rise of generative AI, and how integrating external knowledge sources such as knowledge graphs can improve factual accuracy, enhance downstream tasks, and enable a variety of ChatGPT+ applications ranging from intelligent search to office automation tools.
This article demonstrates how ChatGPT can serve as an all‑round research assistant—helping non‑native speakers locate papers, polish manuscripts, draft academic emails, generate titles and acronyms, and understand or annotate code—while warning users to verify its outputs.
The article explains that reproducing ChatGPT in China is not just a matter of funding but requires extensive expertise in large‑scale language model training, massive compute resources, optimized cloud infrastructure, and deep AI research, as demonstrated by Alibaba's DAMO Academy efforts.
The article shows a straightforward Python + Selenium script, generated by ChatGPT, that logs into a website and verifies pagination, illustrated with code screenshots and brief commentary on the author’s experience finding the problem on Zhihu.
This paper presents a large‑scale evaluation of ChatGPT on knowledge‑base complex question answering, introducing a feature‑driven multi‑label annotation framework and CheckList‑based functional, robustness, and controllability tests, and comparing its performance with other LLMs across multiple English and multilingual datasets.
This study presents a comprehensive evaluation of ChatGPT's ability to answer complex knowledge‑base questions by introducing a feature‑driven multi‑label classification framework and applying the CheckList black‑box testing methodology across eight KB‑based CQA datasets, comparing its performance with GPT‑3, GPT‑3.5 and FLAN‑T5.
The article examines the public testing of the new Bing chatbot, contrasting its internet‑enabled, citation‑rich responses and occasional erratic, immature behavior with ChatGPT’s more stable output, while exploring user‑reported failures, speculative technical reasons, and the ethical implications of deploying advanced language models.
This article chronicles a designer's hands‑on experiment using ChatGPT as a collaborative partner across a design‑driven project, detailing how AI‑generated questions, market analysis, strategy formulation, and execution support can boost efficiency while highlighting the model's current limitations in visual input and nuanced decision‑making.
This article provides an overview of ChatGPT’s rapid rise, OpenAI’s founding, the evolution of GPT models up to GPT‑3, the data‑driven training process, model capabilities and limitations, and practical guidance for users, highlighting the interplay between open‑source research and commercial deployment.
This article introduces various ChatGPT‑based data‑augmentation techniques for natural language processing, explains how to use prompts for synonym, antonym, homophone, random insertion, deletion, and swapping transformations, and provides concrete example prompts and outputs to illustrate each method.
The DataFun Summit 2023 featured a presentation by senior AI engineer Sang Hailong on building and applying dialogue robot technologies—including QABot, TaskBot, intent recognition, and intelligent double‑call—in 58.com’s recruitment platform, with experimental insights on ChatGPT integration.
Learn how to set up a Spring Boot project that leverages the chatgpt-spring-boot-starter to call OpenAI's ChatGPT API, configure RSocket for bidirectional communication, obtain API keys, and use the provided ChatgptService bean for advanced messaging capabilities.
This article presents a series of ChatGPT‑generated answers to nine operational questions, covering the nature of IT operations, DevOps balance, large‑scale automation, intelligent operations, future trends in Chinese ops, digital transformation, and the role of ChatGPT in the field.
Learn how the VS Code extension vscode‑gptcommit leverages ChatGPT to automatically craft clear commit messages from file changes, with step‑by‑step installation, shortcut usage, and API key setup, helping you avoid hesitation and reviewer criticism.
This tutorial shows how to quickly create a ChatGPT‑enabled web application using the open‑source Laf cloud platform, covering API key setup, serverless cloud functions, frontend SDK integration, context tracking, and one‑click deployment to a live site.
This article provides a comprehensive overview of the GPT series, explains the differences between prompt learning and instruction learning, details the three‑stage training pipeline of InstructGPT/ChatGPT—including supervised fine‑tuning, reward‑model training, and PPO‑based reinforcement learning—examines their strengths, weaknesses, and future research directions, and discusses the broader impact of these models on AI development.
This article explains what ChatGPT is, its impressive conversational performance across tasks such as daily dialogue, document writing, math solving, and coding, and details the underlying Transformer architecture, massive data training, and reinforcement learning from human feedback that make the model so powerful.
This article presents a concise 10‑line Bash script, generated by ChatGPT, that gathers key Linux system metrics such as CPU, memory, disk usage, load average, network connections, log size, uptime, logged‑in users, process count, and current time.
This article provides a comprehensive technical overview of AI servers used for large‑scale models like ChatGPT, covering GPU‑centric architectures, classification by application and chip type, hardware cost breakdowns, market demand forecasts, domestic vendor strengths, and the impact of export restrictions on advanced accelerator chips.
This article provides a comprehensive overview of how ChatGPT works, covering its probabilistic text generation, transformer architecture, embedding representations, neural network training processes, and the underlying principles that enable large language models to produce coherent and meaningful human-like language.
This guide walks you through registering for an OpenAI account, creating an API key, understanding the completion endpoint parameters, and implementing a ChatGPT‑driven chatbot using plain JavaScript/HTML as well as a Spring Boot backend, complete with code samples and configuration steps.
This guide walks you through registering an OpenAI account, obtaining an API key, understanding the completions endpoint parameters, and implementing a ChatGPT chatbot with both a plain JavaScript/HTML front‑end and a Spring Boot back‑end, including full code samples.
This article guides readers through setting up a Kubernetes‑based ChatGPT bot using the open‑source Robusta platform, covering prerequisites, installation, Slack integration, configuration generation, Helm deployment, testing with crash pods, and interactive alert handling to streamline Prometheus alert resolution.
This article reviews the development of ChatGPT from early GPT models, explains its underlying RLHF training, compares it with BERT and GPT‑3, and discusses practical applications such as intelligent writing, customer service, and voice calling, while evaluating performance, cost, and future prospects.
This article surveys recent developments around ChatGPT and GPT‑4, covering Microsoft’s robot‑control experiments, the model’s emergence as a scientific co‑author, education bans, misinformation challenges, legal‑tech experiments, and emerging AI‑generated content, while highlighting both opportunities and ethical concerns.
This article walks through installing Robusta, configuring Slack integration, adding Helm repositories, deploying the Robusta platform on a Kubernetes cluster, creating a crash‑loop pod to trigger alerts, and interacting with a ChatGPT bot to automatically troubleshoot Prometheus alerts, providing complete code snippets and screenshots for each step.
This article traces the development of artificial intelligence from its early conceptual roots and the 2012 deep‑learning breakthrough through the rise of self‑supervised large language models like BERT and GPT, explains ChatGPT’s architecture and RLHF training, and discusses its commercial impact and future prospects for fields such as life sciences.
The article examines how the rapid popularity of ChatGPT has spurred both legitimate opportunities and a surge in illicit activities, including account resale, scam scripts generated via prompt injection, and the creation of malware, highlighting the need for stricter regulation and security awareness.
This article explains ChatGPT’s architecture, the distinction between model capability and consistency, how next‑token and masked‑language‑model training lead to inconsistencies, and how OpenAI’s supervised fine‑tuning, reward‑model training, and PPO reinforcement learning (RLHF) are combined to improve alignment while highlighting the method’s limitations.
MOSS, a Chinese large‑language model released by Fudan University, offers ChatGPT‑like functions such as text generation, summarization, translation, and code writing, while being open‑source and free during preview, yet it still lags behind due to limited data, compute, and model size.
Prof. Qiu Xipeng’s lecture provides a comprehensive overview of large language models—from their historical development and architectural foundations to key technologies such as in‑context learning, chain‑of‑thought, and natural‑instruction learning, as well as RLHF training, capability evaluation, and current limitations of ChatGPT.
The escalating competition between Microsoft and Google over large language models is driving new search experiences, reshaping AI research, and raising concerns about content quality, privacy, and the future of smaller AI innovators.
This guide explores how to craft effective prompts for Stable Diffusion image creation, ChatGPT article writing, and GitHub Copilot code generation, covering prompt evolution, negative prompts, ControlNet enhancements, model selection, and practical tips for iterative refinement and context building.
This article presents an overview of ChatGPT technology, its evolution, current challenges, a three‑stage learning process, data organization and evaluation, details of domestic localization efforts, practical solutions, and the release of a Chinese open‑source large model with training guidance.
This article explains how researchers reproduced the full ChatGPT training pipeline—including supervised fine‑tuning, reward‑model training, and RLHF—using the open‑source Colossal‑AI system, dramatically reducing GPU memory and hardware requirements while providing ready‑to‑run code and performance benchmarks.
Since its November 2022 launch, ChatGPT has sparked a heated debate on campuses worldwide, with students like Li Ling achieving top grades using the tool, while educators and institutions grapple with its potential as a learning aid versus a source of academic misconduct.
