How is education GPT created?
In January 2024, OpenAI officially announced that GPTs (mall) will be officially launched.
Therefore, the threshold for programmers has been lowered again. As long as there is enough creativity and imagination, the era has come when everyone can create a GPT tool based on their own professional knowledge.
Using GPTs to conduct research on online education categories has risen rapidly and has become a popular category recommended by officials. In this category, the top ones on the hot list are mathematics GPT, physics GPT, language teaching GPT, video summary GPT, data analysis GPT, and comprehensive GPT in various disciplines.
Among them, there is even a GPT that teaches you how to write prompt words.
Looking at the top 12 GPT products in the education category, mathematics problem solving and language teaching are the two most popular applications.
As of March 2024, only pure mathematics GPT is on the hot list. There are two types, namely math and Math Solver. Language GPT includes Japanese GPT, Korean GPT, and languages that support 20 languages. Teacher GPT──Language Teacher | Ms. Smith.
AI为题目
# Zhiding.com found two 2023 National College Entrance Examination mathematics questions for testing on the two GPTs of math and Math Solver. Let’s see what they can give What an answer.
For the first question, we select the first multiple-choice question from the liberal arts mathematics test paper of the 2023 National College Entrance Examination Paper A. The questions are as follows:
Use math to answer When, it quickly gave the answer:
This is a mathematical question about collective knowledge, and it is also a simple multiple choice question. When solving the problem, math first The topic is briefly described, then briefly analyzed, and finally a calculated answer is given, which is very close to human thinking and logic and is also a normal teaching idea.
In response to this question, the answer given by Math Solver is:
Math Solver gives a complete solution to the problem in three steps. It also provides key concepts, explanations of key concepts, and related exercises. Such problem-solving steps are obviously more suitable for beginners.
However, as far as this question is concerned, the two gave different answers, and the correct answer to this question is A. Obviously, the problem-solving steps given by Math Solver are detailed, but from the perspective of logic and In terms of problem-solving ability, Math Solver still has some shortcomings.
For the second question, we also choose the answer question on this paper that is worth 12 points and involves function calling:
math gives The answer is as follows:
The problem-solving ideas given by Math Solver are as follows:
From the perspective of problem-solving ideas, Although the problem-solving process of math is not concise enough, the problem-solving ideas are more natural and basically conform to human logic and problem-solving steps;
Math Solver adopts a step-by-step problem-solving method as always, but in the problem-solving process In many cases, errors occurred when calling the automatic solver, and the logical thinking during the problem-solving process was obviously not "mathematical" enough, and the expressions were long-winded and imprecise.
Judging from the results, both mathematical GPTs failed to give an answer.
However, it is worth noting that although these two mathematical GPTs failed to give the correct answer, they did not make up an answer. This is obviously because the GPT designer added some precautions in the prompt words. Prompt word for GPT hallucination.
In addition, we tested Language Teacher | Ms. Smith. During the test, it will first ask you what language you want to learn, then it will ask whether you are a beginner or an advanced person, and then it will ask Give some topic suggestions.
In this process, it will default to your native language being English, and will talk to you in English first. After selecting the topic, it will communicate with you in the language you selected, and will also correct your grammatical expressions. mistake.
The actual use experience of such language GPT is obviously better than that of mathematics GPT.
In fact, although today’s GPT has a certain degree of versatility after training based on a large amount of professional data, even the top-ranked teaching GPT among GPTs is still closer to " Language teaching in “small talk” scenarios.
Let Qin Shihuang teach Chinese
In order to facilitate users to develop GPT applications, OpenAI actually embeds the GPT application development platform into GPTs. Through this development platform, novice users You can also design a GPT application step by step in the guided step.
We used this development platform in GPTs and drew on the teaching design logic of Language Teacher | Ms. Smith, and also tried to design a Chinese teaching GPT - Qin Shi Huang Taught Chinese. The following is how we designed this GPT Prompt words used:
First, create a GPT to help English native speakers learn Chinese. The name of the GPT is Qin Shihuang Teaches Chinese. The image should imitate the ancient Chinese emperor. The image of the emperor should be humorous. The emperor holds a hand in his hand. A book with the words Learn Chinese Easily in English and Simplified Chinese on the cover.
Secondly, every time you open this GPT, GPT will first ask:
Hi, nice to see you, please tell me your Chinese language level:
- Beginner (Beginner)
- Intermediate (Intermediate)
- Advanced (Advanced)
Then, after the user selects, continue to prompt the user for dialogue type selection:
Here are the topics we can cover at the intermediate level:
Travel and Culture: Discuss travel experiences, cultural differences, and learn vocabulary about transportation, accommodation, and tourist attractions.
Current Events: Engage in discussions about recent news, focusing on vocabulary related to politics, environment, and society. Express opinions and perspectives.
The Professional World: Talk about various professions, workplace scenarios, and job-related tasks, using industry-specific vocabulary.
Health and Well-being: Discuss health, fitness, and lifestyle choices. Includes medical terms, fitness activities, and health-related habits.
Mock Job Interview: Participate in a simulated job interview, practicing questions and answers common job interviews. This includes learning formal language and industry-specific terminology.
Next, after the user selects the user’s language level and conversation type, actively use the corresponding Language level and conversation type communicate with users on corresponding topics.
After the user selects the user's language level and conversation type, take the initiative to use the corresponding language level and conversation type to communicate with the user on the corresponding topic. During the communication process, a mixture of Chinese and English is used, for example:
Have you been to any interesting places recently? (Have you visited any interesting places recently?)
Finally, after the user answers, first compare the user's answer with the expressions in the fifth edition of "Modern Chinese Dictionary". If the content of the user's answer The expression is not standard, correct the corresponding content first, and then continue the topic, for example:
The first step to correct the error:?Better expression: saw the begonia bloomingcould be more naturally expressed as "see the begonia blooming" .
The second step is to continue the topic chat: That sounds very interesting! The ski resorts near Los Angeles are also famous. It must be beautiful to see begonia flowers blooming, right? Where else do you plan to travel?
The Chinese teaching GPT "Qin Shihuang Teaches Chinese" designed through such a set of prompt words, after the design is completed, basic Chinese teaching can be carried out in a decent manner.
Obviously, even if you don’t buy an AI course worth several thousand yuan, ordinary people can easily develop a decent GPT on the development platform built by OpenAI.
This makes people sigh that the era of artificial intelligence has really arrived.
The above is the detailed content of How is education GPT created?. For more information, please follow other related articles on the PHP Chinese website!
Hot AI Tools
Undresser.AI Undress
AI-powered app for creating realistic nude photos
AI Clothes Remover
Online AI tool for removing clothes from photos.
Undress AI Tool
Undress images for free
Clothoff.io
AI clothes remover
Video Face Swap
Swap faces in any video effortlessly with our completely free AI face swap tool!
Hot Article
Hot Tools
Notepad++7.3.1
Easy-to-use and free code editor
SublimeText3 Chinese version
Chinese version, very easy to use
Zend Studio 13.0.1
Powerful PHP integrated development environment
Dreamweaver CS6
Visual web development tools
SublimeText3 Mac version
God-level code editing software (SublimeText3)
Hot Topics
1386
52
Bytedance Cutting launches SVIP super membership: 499 yuan for continuous annual subscription, providing a variety of AI functions
Jun 28, 2024 am 03:51 AM
This site reported on June 27 that Jianying is a video editing software developed by FaceMeng Technology, a subsidiary of ByteDance. It relies on the Douyin platform and basically produces short video content for users of the platform. It is compatible with iOS, Android, and Windows. , MacOS and other operating systems. Jianying officially announced the upgrade of its membership system and launched a new SVIP, which includes a variety of AI black technologies, such as intelligent translation, intelligent highlighting, intelligent packaging, digital human synthesis, etc. In terms of price, the monthly fee for clipping SVIP is 79 yuan, the annual fee is 599 yuan (note on this site: equivalent to 49.9 yuan per month), the continuous monthly subscription is 59 yuan per month, and the continuous annual subscription is 499 yuan per year (equivalent to 41.6 yuan per month) . In addition, the cut official also stated that in order to improve the user experience, those who have subscribed to the original VIP
Context-augmented AI coding assistant using Rag and Sem-Rag
Jun 10, 2024 am 11:08 AM
Improve developer productivity, efficiency, and accuracy by incorporating retrieval-enhanced generation and semantic memory into AI coding assistants. Translated from EnhancingAICodingAssistantswithContextUsingRAGandSEM-RAG, author JanakiramMSV. While basic AI programming assistants are naturally helpful, they often fail to provide the most relevant and correct code suggestions because they rely on a general understanding of the software language and the most common patterns of writing software. The code generated by these coding assistants is suitable for solving the problems they are responsible for solving, but often does not conform to the coding standards, conventions and styles of the individual teams. This often results in suggestions that need to be modified or refined in order for the code to be accepted into the application
Can fine-tuning really allow LLM to learn new things: introducing new knowledge may make the model produce more hallucinations
Jun 11, 2024 pm 03:57 PM
Large Language Models (LLMs) are trained on huge text databases, where they acquire large amounts of real-world knowledge. This knowledge is embedded into their parameters and can then be used when needed. The knowledge of these models is "reified" at the end of training. At the end of pre-training, the model actually stops learning. Align or fine-tune the model to learn how to leverage this knowledge and respond more naturally to user questions. But sometimes model knowledge is not enough, and although the model can access external content through RAG, it is considered beneficial to adapt the model to new domains through fine-tuning. This fine-tuning is performed using input from human annotators or other LLM creations, where the model encounters additional real-world knowledge and integrates it
Posthumous work of the OpenAI Super Alignment Team: Two large models play a game, and the output becomes more understandable
Jul 19, 2024 am 01:29 AM
If the answer given by the AI model is incomprehensible at all, would you dare to use it? As machine learning systems are used in more important areas, it becomes increasingly important to demonstrate why we can trust their output, and when not to trust them. One possible way to gain trust in the output of a complex system is to require the system to produce an interpretation of its output that is readable to a human or another trusted system, that is, fully understandable to the point that any possible errors can be found. For example, to build trust in the judicial system, we require courts to provide clear and readable written opinions that explain and support their decisions. For large language models, we can also adopt a similar approach. However, when taking this approach, ensure that the language model generates
To provide a new scientific and complex question answering benchmark and evaluation system for large models, UNSW, Argonne, University of Chicago and other institutions jointly launched the SciQAG framework
Jul 25, 2024 am 06:42 AM
Editor |ScienceAI Question Answering (QA) data set plays a vital role in promoting natural language processing (NLP) research. High-quality QA data sets can not only be used to fine-tune models, but also effectively evaluate the capabilities of large language models (LLM), especially the ability to understand and reason about scientific knowledge. Although there are currently many scientific QA data sets covering medicine, chemistry, biology and other fields, these data sets still have some shortcomings. First, the data form is relatively simple, most of which are multiple-choice questions. They are easy to evaluate, but limit the model's answer selection range and cannot fully test the model's ability to answer scientific questions. In contrast, open-ended Q&A
SOTA performance, Xiamen multi-modal protein-ligand affinity prediction AI method, combines molecular surface information for the first time
Jul 17, 2024 pm 06:37 PM
Editor | KX In the field of drug research and development, accurately and effectively predicting the binding affinity of proteins and ligands is crucial for drug screening and optimization. However, current studies do not take into account the important role of molecular surface information in protein-ligand interactions. Based on this, researchers from Xiamen University proposed a novel multi-modal feature extraction (MFE) framework, which for the first time combines information on protein surface, 3D structure and sequence, and uses a cross-attention mechanism to compare different modalities. feature alignment. Experimental results demonstrate that this method achieves state-of-the-art performance in predicting protein-ligand binding affinities. Furthermore, ablation studies demonstrate the effectiveness and necessity of protein surface information and multimodal feature alignment within this framework. Related research begins with "S
SK Hynix will display new AI-related products on August 6: 12-layer HBM3E, 321-high NAND, etc.
Aug 01, 2024 pm 09:40 PM
According to news from this site on August 1, SK Hynix released a blog post today (August 1), announcing that it will attend the Global Semiconductor Memory Summit FMS2024 to be held in Santa Clara, California, USA from August 6 to 8, showcasing many new technologies. generation product. Introduction to the Future Memory and Storage Summit (FutureMemoryandStorage), formerly the Flash Memory Summit (FlashMemorySummit) mainly for NAND suppliers, in the context of increasing attention to artificial intelligence technology, this year was renamed the Future Memory and Storage Summit (FutureMemoryandStorage) to invite DRAM and storage vendors and many more players. New product SK hynix launched last year
Laying out markets such as AI, GlobalFoundries acquires Tagore Technology's gallium nitride technology and related teams
Jul 15, 2024 pm 12:21 PM
According to news from this website on July 5, GlobalFoundries issued a press release on July 1 this year, announcing the acquisition of Tagore Technology’s power gallium nitride (GaN) technology and intellectual property portfolio, hoping to expand its market share in automobiles and the Internet of Things. and artificial intelligence data center application areas to explore higher efficiency and better performance. As technologies such as generative AI continue to develop in the digital world, gallium nitride (GaN) has become a key solution for sustainable and efficient power management, especially in data centers. This website quoted the official announcement that during this acquisition, Tagore Technology’s engineering team will join GLOBALFOUNDRIES to further develop gallium nitride technology. G
