Technology peripherals
AI
ByteDance releases 'Doubao MarsCode” intelligent development tool, free for domestic developers
ByteDance releases 'Doubao MarsCode” intelligent development tool, free for domestic developers
On June 26, ByteDance released Doubao MarsCode, an intelligent development tool based on the Doubao large model, in Beijing, which is free and open to domestic developers. With the theme of "Inspiring Creation with AI", this conference released the beanbag MarsCode and introduced its main functions in the relaxed atmosphere of grass camping. It also released a developer and community co-creation plan, attracting many industry professionals and developers. and the attention of technology enthusiasts.
Doubao MarsCode product launch event
Doubao MarsCode - Use AI to inspire creation
Li Dongjiang, head of Bytedance Developer Service Team and Doubao MarsCode
Before the official release, Li Dongjiang, the Bytedance developer service team and the person in charge of Doubao MarsCode, shared some thoughts on the evolution of development tools in the AI era.
In the AI era, large language models have strong advantages and potential in programming languages. Compared with complex natural languages, programming languages are simpler, more rigorous, and more predictable. of.
Regarding the proposition of "how to build a developer tool in the AI era", the Doubao MarsCode team will focus more on how to empower development Start from the perspective of the author. Li Dongjiang believes that AI is not a "competitor" to replace developers, but a "good helper" for developers . The team hopes to create a software that It can help improve developer work efficiency and allow developers to have more energy and time for thinking and creating. This is why the theme of the conference is "Using AI to Inspire Creation."
Li Dongjiang mentioned that new models, new computing power, new products, and new technologies are emerging every day, no matter the product As for technology, everything is still in its early stages and is being updated and iterated rapidly. Driven by AI technology, the next generation of development tools will definitely emerge. The Doubao MarsCode team hopes to explore and build together with developers to create new developer tools in the AI era.
Doubao MarsCode’s first release function revealed
Wang Haijian, product manager of Doubao MarsCode
Subsequently, Wang Haijian, product manager of Doubao MarsCode, introduced the two forms of Doubao MarsCode products - programming assistant and Cloud IDE. At the same time, he demonstrated Doubao in detail through three actual scenarios of demand development, bug fixing, and open source project learning. MarsCode's project Q&A, code completion, single test generation, Bug Fix and other functions. Through a complete scenario demonstration, the use and cooperation of various functions in series demonstrate the excellent implementation ability of Doubao MarsCode in daily work. Both novice programmers and experienced developers can experience the assistance and efficiency improvement brought by Doubao MarsCode.
Requirement Development Scenario
Through a practical case of translation robot construction, Wang Haijian demonstrated how, with the assistance of AI, developers can invoke programming assistants to ask questions via Chat, analyze requirements, become familiar with code, write code, and debug code.
Code completion can not only help developers enter code faster, but also provide developers with continuous code suggestions. Inspiration and inspiration.
The innovative function of MarsCode - Code Completion Pro, unlike traditional code continuation, supports automatic prediction based on user editing intentions. A change point and code recommendations are given.
In addition to code prediction and completion, when there is a code Lint error that needs to be repaired in coding, the programming assistant will directly By actively providing the modified code in the editor, we do not need to check the cause of the error. We only need to determine whether the repair result is correct. If it is correct, we can adopt the repaired code with one click.
Finally, when we finish writing the code, in order to ensure the quality and subsequent maintainability of the code, we usually need to write unit tests. At this time, you only need to trigger test in the programming assistant to get the test case for this function.
As you can see, compared to traditional development methods, Doubao MarsCode programming assistant can help developers program more easily and more focused.
Bug Repair Scenario
In the Debug scenario, the AI repair function of Doubao MarsCode can understand the error message, The call stack code and global project code are used to analyze the cause of the error and directly provide targeted repair suggestions.
En plus de la réparation en un seul tour, Doubao MarsCode tente également de mettre en œuvre plusieurs cycles de réparation automatique basés sur la méthode Agent AI qui appellera de manière autonome une série de requêtes de code. outils et outils de débogage pour obtenir des informations sur les erreurs, planifier le plan de manière indépendante, écrire le code de manière indépendante et l'appliquer au projet pour corriger les bugs. Cette fonction est actuellement vérifiée en interne par Byte et nous nous efforçons de la rendre accessible à tous dès que possible.
Scénario d'apprentissage de projet open source
Dans le troisième scénario, Doubao MarsCode IDE permet aux développeurs de se lancer rapidement dans des projets sans exploiter ni maintenir un environnement local en fournissant des modèles de développement. Grâce aux capacités d'IA intégrées nativement, les développeurs n'ont plus besoin de comprendre le code eux-mêmes, ce qui leur permet de démarrer des projets plus efficacement.
En général, le pouf MarsCode aide les développeurs dans les deux aspects suivants :
Pour la phase de réflexion, fournir de meilleures informations, telles que des explications de code et des questions et réponses sur les connaissances en R&D, pour inciter les développeurs à créer
Pour la phase de réalisation, il aide les développeurs à terminer le codage plus rapidement, comme l'achèvement du code et la prédiction de la prochaine action de codage, les corrections d'erreurs de code pour améliorer l’efficacité des développeurs.
Plan de co-création des développeurs et de la communauté
Zhao Xudong, responsable des opérations de marché de Doubao MarsCode
Enfin, Zhao Xudong, responsable des opérations de marché de Doubao MarsCode, a présenté le développement du programme de co-création Doubao MarsCode avec la communauté. À l'avenir, MarsCode aidera les développeurs à explorer de nouveaux paradigmes de programmation de l'IA grâce à la création de groupes d'utilisateurs et à diverses séries d'activités de développement.
Le groupe d'utilisateurs Doubao MarsCode sera auto-organisé et géré par des développeurs. L'équipe Doubao MarsCode ne participera pas à la gestion du groupe d'utilisateurs, mais fournira au groupe d'utilisateurs de riches ressources et soutiendra le développement de. des groupes d'utilisateurs à divers endroits, tels que les ressources du site, les ressources sur les produits, le matériel événementiel, le soutien de conférenciers experts, etc. aident à encourager les développeurs du monde entier à explorer plus efficacement les nouveaux paradigmes de programmation de l'IA et aident nos développeurs à apprendre et à grandir.
En termes d'activités de développement, Doubao MarsCode organisera successivement des Meetups à Pékin, Shanghai, Shenzhen, Hangzhou et d'autres villes, et quittera le salle de conférence avec des développeurs Sortez, échangez des compétences et des expériences en programmation d'IA de manière plus détendue et utilisez l'IA pour inspirer la créativité ensemble !
Doubao MarsCode prévoit également de collaborer avec diverses communautés de développeurs pour intégrer les capacités d'IA dans les scénarios d'utilisation de la communauté et fournir les capacités de Doubao MarsCode plus facilement aux développeurs. . À l'heure actuelle, Doubao MarsCode a coopéré avec la communauté Nuggets sur les assistants IA, l'ouverture de compte et les zones de point d'ébullition exclusives. Dans le même temps, nous espérons également coopérer et co-créer avec davantage de communautés, afin que les capacités d'IA de Doubao MarsCode puissent être étendues à davantage de scénarios communautaires, apportant la prochaine génération de paradigme de programmation à davantage de développeurs, aidant les développeurs à soyez plus rapide et plus efficace !
Doubao MarsCode a été officiellement publié le 26 juin. Cliquez pour lire le texte original ou copier et visiter le site officiel (www.marscode.cn) pour l'utiliser
Nous tirerons au sort 66 utilisateurs chanceux parmi les utilisateurs qui se sont inscrits avec succès avant 23h59 le jour de la sortie pour recevoir un pouf Périphérique personnalisé MarsCode~
Utilisez l'IA pour inspirer la créativité et ouvrir un nouveau chapitre dans le codage intelligent. L'équipe Doubao MarsCode espère utiliser de nouveaux produits pour mieux servir les utilisateurs, améliorer l'efficacité et utiliser l'IA pour inspirer plus de créativité et de passion.
|
|
(Aller pour lire le texte original Lien de redirection : https://www.marscode.cn/home??utm_source=626&utm_medium=wx)
The above is the detailed content of ByteDance releases 'Doubao MarsCode” intelligent development tool, free for domestic developers. 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
1664
14
1421
52
1315
25
1266
29
1239
24
The author of ControlNet has another hit! The whole process of generating a painting from a picture, earning 1.4k stars in two days
Jul 17, 2024 am 01:56 AM
It is also a Tusheng video, but PaintsUndo has taken a different route. ControlNet author LvminZhang started to live again! This time I aim at the field of painting. The new project PaintsUndo has received 1.4kstar (still rising crazily) not long after it was launched. Project address: https://github.com/lllyasviel/Paints-UNDO Through this project, the user inputs a static image, and PaintsUndo can automatically help you generate a video of the entire painting process, from line draft to finished product. follow. During the drawing process, the line changes are amazing. The final video result is very similar to the original image: Let’s take a look at a complete drawing.
Topping the list of open source AI software engineers, UIUC's agent-less solution easily solves SWE-bench real programming problems
Jul 17, 2024 pm 10:02 PM
The AIxiv column is a column where this site publishes academic and technical content. In the past few years, the AIxiv column of this site has received more than 2,000 reports, covering top laboratories from major universities and companies around the world, effectively promoting academic exchanges and dissemination. If you have excellent work that you want to share, please feel free to contribute or contact us for reporting. Submission email: liyazhou@jiqizhixin.com; zhaoyunfeng@jiqizhixin.com The authors of this paper are all from the team of teacher Zhang Lingming at the University of Illinois at Urbana-Champaign (UIUC), including: Steven Code repair; Deng Yinlin, fourth-year doctoral student, researcher
From RLHF to DPO to TDPO, large model alignment algorithms are already 'token-level'
Jun 24, 2024 pm 03:04 PM
The AIxiv column is a column where this site publishes academic and technical content. In the past few years, the AIxiv column of this site has received more than 2,000 reports, covering top laboratories from major universities and companies around the world, effectively promoting academic exchanges and dissemination. If you have excellent work that you want to share, please feel free to contribute or contact us for reporting. Submission email: liyazhou@jiqizhixin.com; zhaoyunfeng@jiqizhixin.com In the development process of artificial intelligence, the control and guidance of large language models (LLM) has always been one of the core challenges, aiming to ensure that these models are both powerful and safe serve human society. Early efforts focused on reinforcement learning methods through human feedback (RL
arXiv papers can be posted as 'barrage', Stanford alphaXiv discussion platform is online, LeCun likes it
Aug 01, 2024 pm 05:18 PM
cheers! What is it like when a paper discussion is down to words? Recently, students at Stanford University created alphaXiv, an open discussion forum for arXiv papers that allows questions and comments to be posted directly on any arXiv paper. Website link: https://alphaxiv.org/ In fact, there is no need to visit this website specifically. Just change arXiv in any URL to alphaXiv to directly open the corresponding paper on the alphaXiv forum: you can accurately locate the paragraphs in the paper, Sentence: In the discussion area on the right, users can post questions to ask the author about the ideas and details of the paper. For example, they can also comment on the content of the paper, such as: "Given to
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
A significant breakthrough in the Riemann Hypothesis! Tao Zhexuan strongly recommends new papers from MIT and Oxford, and the 37-year-old Fields Medal winner participated
Aug 05, 2024 pm 03:32 PM
Recently, the Riemann Hypothesis, known as one of the seven major problems of the millennium, has achieved a new breakthrough. The Riemann Hypothesis is a very important unsolved problem in mathematics, related to the precise properties of the distribution of prime numbers (primes are those numbers that are only divisible by 1 and themselves, and they play a fundamental role in number theory). In today's mathematical literature, there are more than a thousand mathematical propositions based on the establishment of the Riemann Hypothesis (or its generalized form). In other words, once the Riemann Hypothesis and its generalized form are proven, these more than a thousand propositions will be established as theorems, which will have a profound impact on the field of mathematics; and if the Riemann Hypothesis is proven wrong, then among these propositions part of it will also lose its effectiveness. New breakthrough comes from MIT mathematics professor Larry Guth and Oxford University
The first Mamba-based MLLM is here! Model weights, training code, etc. have all been open source
Jul 17, 2024 am 02:46 AM
The AIxiv column is a column where this site publishes academic and technical content. In the past few years, the AIxiv column of this site has received more than 2,000 reports, covering top laboratories from major universities and companies around the world, effectively promoting academic exchanges and dissemination. If you have excellent work that you want to share, please feel free to contribute or contact us for reporting. Submission email: liyazhou@jiqizhixin.com; zhaoyunfeng@jiqizhixin.com. Introduction In recent years, the application of multimodal large language models (MLLM) in various fields has achieved remarkable success. However, as the basic model for many downstream tasks, current MLLM consists of the well-known Transformer network, which
LLM is really not good for time series prediction. It doesn't even use its reasoning ability.
Jul 15, 2024 pm 03:59 PM
Can language models really be used for time series prediction? According to Betteridge's Law of Headlines (any news headline ending with a question mark can be answered with "no"), the answer should be no. The fact seems to be true: such a powerful LLM cannot handle time series data well. Time series, that is, time series, as the name suggests, refers to a set of data point sequences arranged in the order of time. Time series analysis is critical in many areas, including disease spread prediction, retail analytics, healthcare, and finance. In the field of time series analysis, many researchers have recently been studying how to use large language models (LLM) to classify, predict, and detect anomalies in time series. These papers assume that language models that are good at handling sequential dependencies in text can also generalize to time series.
