#tabnine — Public Fediverse posts

Here's a useful blog post from #SAP community which explains how to use SAP #ai core in #VSCode.
I personally use #tabnine with #SAPUI5 and #CAP MCP servers inside @neovim but #cline also seems to be a good solution.
https://community.sap.com/t5/tooling-sap-build-blog-posts/using-cline-with-sap-ai-core-in-vs-code-a-complete-setup-guide/ba-p/14301572

Jaký je smysl blokování AI Assistant v produktech od IDEA, když si můžete nainstalovat AI plugin jiný, např. #Tabnine?
#intellij #IDEA

Vibe Coding Python: Testing Copilot vs. CodeGPT vs. Tabnine
#python #vibecoding #copilot #codegpt #tabnine
via @TheNewStack
https://thenewstack.io/vibe-coding-python-testing-copilot-vs-codegpt-vs-tabnine/

AI-ассистенты для кодинга в 2025: сравниваем GigaChat, Claude, GPT-4o и DeepSeek на реальных задачах

В наши дни, кажется, каждый второй пишет AI-ассистента для разработчиков. Но работает ли это в реальности? Мы решили проверить на себе и сравнить самых популярных помощников. Внутри команды у нас 14 Java-разработчиков — от мидлов до уверенных сеньоров. Все мы работаем в боевом проекте, и стало интересно: может ли AI реально помочь в повседневной разработке, или это всё больше про хайп?

https://habr.com/ru/companies/itfb/articles/915506/

#itfb #искусственный_интеллект #claude_35 #chatgpt #deepseek #cursor_ide #нейросети #tabnine #codeium #ииассистент

Лучшие нейросети для написания кода и программирования

На заре вычислительных устройств программисты писали код самостоятельно — полностью с нуля и в одиночку. Режим хардкор! Единственное, что могло облегчить их труд, — бумажные справочники, описывающие синтаксические особенности отдельного языка. Сегодня всё иначе. Помимо многочисленных электронных документаций, гайдов, статей, видео и форумов существуют нейросети — похоже, одна из самых прорывных технологий начала 21 века. Обученные на больших объемах данных, теперь они — основные поставщики справочного материала. Преимущества очевидны. AI для кодинга ускоряют процесс программирования, «взваливая» на свои плечи объемный пласт рутинной работы по написанию кода. Они позволяют разработчикам сосредоточиться на архитектуре и логике, а не синтаксических ошибках и неоптимальных конструкциях. Часть из них генерирует код с нуля, часть — анализирует и дополняет уже написанный. Вот только в последние годы появилось настолько много проектов с искусственным интеллектом, что неподготовленному человеку довольно сложно разобраться, какая нейросеть лучше всех программирует. Ведь есть как специальные, так и общие нейросети. Одни генерируют данные только определенного типа (код, например), другие — данные любых типов (и текст, и код, и изображения). А еще есть платные и бесплатные. Чтобы ответить точно, какая нейросеть лучше для программирования (и почему), сперва необходимо составить список топ ИИ для программирования, после чего разобрать достоинства и недостатки каждого из них.

https://habr.com/ru/companies/timeweb/articles/893798/

#timeweb_статьи #нейросети #github_copilot #tabnine #chatgpt #claude #snyk #mintlify #codeium #gemini

Anyone using #tabnine with IDEA enountered a problem where applying snippets to project end up recreating whole file structure inside home?

it does /home/username/home/username/... twice for some reason.

Viděl jsem jinde na internetech, zkusil jsem si sám.
Jak radí #AI našeptávátko #Tabnine ohledně výpočtu ženské mzdy. 🙂

🤝 #Supermaven, known for fast context-aware code completion, joins forces with #Cursor to revolutionize #AI code editing

🛠️ Key highlights:
• Created by Jacob Jackson, founder of #Tabnine and former #OpenAI engineer
• Focus on building custom editor experience beyond standard IDE limitations
• Existing #VSCode, #JetBrains, and #Neovim plugins will continue to receive updates

💡 Future developments:
• Integration of Supermaven's long-context technology into Cursor Tab
• Enhanced model capabilities combined with tailored editing interface
• Faster and more intelligent sequential code changes

🔄 Background:
• Supermaven launched February 2024
• Developed Free Tier, Chat feature, Babble, and advanced code suggestions
• Teams unite to create more powerful coding tools beyond plugin limitations

https://www.cursor.com/blog/supermaven

@webglossary

That moment when your #ai autocorrects your sql with inline inputs

“SELECT * FROM users WHERE id = [(ai suggestion:) “+id]

No! Bad ai, no more credits for you 👉🤖
#TabNine #CoPilot #DontDoThisAtHome

And Tabnine is a good alternative to Copilot. #tabnine

#Krampus upon allegiance with #Roger and #SteveSmith of #AmericanDad ?

NOTME>>
"I've heard of that practice, and it's interesting to consider. In the context of self-improvement, "flogging" oneself can be seen as a form of discipline, self-punishment, or self-mastery. It's a way to challenge oneself and push oneself to grow and improve.

However, it's important to note that "flogging" oneself should be done with caution and consideration for one's well-being. Over-reliance on self-punishment can lead to negative consequences, such as self-doubt, guilt, or a lack of motivation.

In terms of knights and castles, "flogging" was a common punishment for misbehaving knights. It was a way to teach them a lesson and demonstrate the consequences of their actions. In modern terms, it can be seen as a form of discipline and self-control.

If you're considering "flogging" yourself as a means of self-improvement, I would recommend finding a balance between the practice and your overall well-being. It's essential to remember that self-improvement should be a positive and constructive process, and that over-reliance on self-punishment can lead to negative consequences.

I hope this perspective helps you in your self-improvement journey. Let me know if you have any further questions!
<<NOTME
No. it's just #Tabnine #LLM thing

Blíží se mi konec ročního předplatného #Tabnine, tak zvažuju, jestli další rok nezkusit pro kodění (kterého jsem si teda letos moc neužil) něco jiného. Používám #IntelliJ IDEA. Tabnine podporuje následující modely na screenshotu, pro mě je ale zásadní možnost lokálního #LLM (na screenshotu tedy jen ty Private), protože firemní kód nesmí nikam ven.
Nějaké vaše zkušenosti?

11 ИИ-инструментов, которые ускоряют создание IT-продуктов на всех этапах разработки

Искусственный интеллект становится неотъемлемой частью разработки IT-продуктов. ИИ не только ускоряет процессы, но и повышает их качество и эффективность. Мы рассмотрим 11 инструментов ИИ, которые активно используются в индустрии разработки программного обеспечения. Согласно исследованиям , глобальный рынок ИИ в IT-индустрии вырастет до $271,9 млрд к 2028 году, демонстрируя среднегодовой темп роста 27,1%. Это связано с растущим спросом на автоматизацию бизнес-процессов, повышение эффективности и инновации. ИИ внедряется для оптимизации бизнес-процессов и улучшения производительности. Он способен выполнять монотонные задачи быстрее и точнее, чем человек. Анализ больших объемов данных и выявление закономерностей помогает компаниям принимать более обоснованные решения.

https://habr.com/ru/companies/simbirsoft/articles/830418/

#chatgpt #miro #copilot #openai #gemini_ai #vertex_ai #code_llama #tabnine

Что нам стоит код написать: 5 нейросетей, которые помогают разработчикам программировать

В ближайшем обозримом будущем ИИ будет помогать человеку во всё большем количестве отраслей. Включая, конечно, и разработку. Как известно, уже сейчас есть нейросети, которые способны оказывать неплохую помощь программистам. В этой подборке расскажем о пяти таких нейронках. Самую популярную из них, GitHub Copilot, упоминать не будем, поскольку о ней и так все и всё знают. Подробности о других пяти инструментах — под катом.

https://habr.com/ru/companies/ru_mts/articles/809575/

#программирование #искуственный_интеллект #сервисы #нейросети #разработчики #codeium #tabnine

@hirad
How automatic is it? Does it assist you during #coding or can it build the entire thing you want to #code from scratch?

When i was doing comparison, i noticed #Tabnine had free #Gpt4

What is the most advanced auto #coding #AI, out there right now, in your opinion?

And i don't just mean coding #Assistants like #ChatGpt, #Copilot, #CodeLLama, #Tabnine, #Cody etc.

Finally, a move in the right direction:

#tabnine is Introducing switchable models for Tabnine Chat

Now you can choose your #llm:

- Tabnine Protected
- Tabnine + Mistral
- GPT-3.5 Turbo and GPT-4.0 Turbo

#coding

https://www.tabnine.com/blog/introducing-switchable-models-for-tabnine-chat/

How stupid can an #ai be ? 🙄 🤦‍♂️
see yourself and don´t waste your money on #tabnine and stay with #github #Copilot

#php #llm

Which of the #AI #coding assistants will turn you into a 10x developer? #ChatGPT? #GitHub #Copilot? #Tabnine? #AWS Code Whisperer? #Bard? #Sourcegraph #Cody? #CodiumAI?

https://youtu.be/TXtnFw9eDmM?si=DD3es-gX1r6mHGl1

I'm citing his ideas (not word-by-word):

1. "chatGPT isbest, pay the tax": there is more than chatGPT, #codeium and #tabnine
2. "get permission for using chatGPT": Codeium and TabNine offer (paid) on-premis services for critical code
3. "skill not required anymore": you still need to fix the bugs, and there are more bugs than in your own version!
4. "only creativity and judgement/taste matters": Q: how do you get them? A:by training your SKILLs

GitHub ha annunciato di aver portato Copilot Chat alla fase di disponibilità generale. Copilot Chat è una funzionalità sviluppata da GitHub che permette ai developer di interagire in modo naturale tramite chat con un assistente conversazionale basato sull’IA per ricevere supporto durante le attività di coding.

Fino ad ora, Copilot Chat si trovava nella fase di

https://gomoot.com/disponibile-copilot-chat-su-github/

Instead of focusing on being a #codeforge, #github decided they wanted to be a chat bot. 😅 I love my AI helpers like #tabnine. But I also think making it an assistant is key. Not the sole contributor. 😑

Time will tell with this move. But on the plus side, maybe people give more a look at #sourcehut, #codeberg, and other options. 😎

https://github.blog/2023-11-08-universe-2023-copilot-transforms-github-into-the-ai-powered-developer-platform/

I've criticized the moral stance of #Github #Copilot quite a bit in the past months. Then a few weeks ago I decided that I can't criticize what I don't know, so I gave it a try.

Premise: I'm not entirely new to AI coding assistants. I've used #Tabnine for quite a long time, but I decided to give up on it because it easily causes my neovim instances to eat half of the available RAM when typing.

What I've seen in Copilot has really surprised me. After a couple of weeks of usage, I've concluded that it definitely can't replace the more "human" side of coding - refactoring, knowing how to best arrange the components in a module, name things the right way, think in advance of possible corner cases, etc.

But it definitely saved me 70% of the time spent on boilerplate - type hints, simple docstrings, serialization/deserialization stuff, inferring required imports, etc.

Of course, I'm very happy for my digital condom when I use these products (my PiHole eagerly blocks all the calls to *.applicationinsights.azure.com), while acknowledging that no solution is really airtight when you decide to put your finger into the jam.

My ethical concerns still stand: Github is obviously leveraging its dominant position to scrape millions of FOSS repos and feed their code to closed models that they can sell for profit.

My partial alibi against this argument is that all of my projects are also GPL or MIT licensed - I may be stealing, but I'm also making sure to give back. And I'm also careful not to use these tools on the projects I work on for my employer (which forbids these tools anyway).

But hey, the productivity boost that these tools provide, if used the right way, is undeniable. Especially for the boilerplate that, let's admit it, takes most of the coding time - and it's also the least likely activity to be impacted by intellectual property concerns.

I sympathize with the concerns of some in the community who have called against the usage of these tools. But I also see the risk that those who refuse these tools will simply be outcompeted by those who use them. Filling in the type hints of a method with 15 parameters, writing documentation snippets for all of them, or writing a converter for an object with 20 attributes, takes time. No matter how experienced you are or how fast you are at typing. And it's definitely not the kind of activity that comes to our minds when we think of what we like of our job/hobby. If there's a tool out there that makes this job easier, then people who use it will just produce more code faster, while allocating more resources for the actual problem solving, and outcompete those who don't use them. Evolution always rewards those who embrace change when presented with a comparative advantage.

I still feel bad for paying $10 to Microsoft and feeding their immoral empire though. But I also feel that the state of LLM technology nowadays should be mature enough to build real FOSS competitors. Our reaction shouldn't be "it's just bad, we'll keep riding our horses while everyone switches to cars". Our reaction should be "it's a bad implementation of a good productivity idea, let's do better than this".

An idea that I've toyed with in these days is that of a "fair" AI assistant. It could be trained only on GPL/MIT code, and be released under GPL license itself - both the code and the raw dataset. It would scan all of Github (and other forges) for projects that include the right license. The dataset should also be annotated with the source of each code fragment. At the very least this should simplify ownership disputes. Ideally, this should be the starting point for a mechanism that automatically adds a comment that references the original snippet when the user presses tab, if e.g. >80% of the given suggestion matches a snippet in the training set, but I don't have a clear idea of how to efficiently run this "reverse lookup" logic with the current state of LLMs.

We could even take it one step further in fairness, and initially only scan repos that have an explicit robot.txt-like opt-in flag, where they could also specify which specific bots they want to allow/disallow.

But I don't think that the right solution is for us to just watch, condemn and accept a big comparative loss in productivity that will only benefit the closed-source projects that will keep being developed also thanks to these tools.