UNIT.City — місце, де люди працюють... КРАЩЕ! Обирай свій простір просто зараз 👉
Валентин ШнайдерAI Eng
24 March 2026, 11:23
2026-03-24
Anthropic adds the ability to open files and work in the user's browser to Claude Code and Cowork
Anthropic has expanded the capabilities of its AI tools Claude Code and Claude Cowork: they can now perform tasks directly on the user’s computer, including opening files, working in the browser, and running developer tools.
Anthropic has expanded the capabilities of its AI tools Claude Code and Claude Cowork: they can now perform tasks directly on the user’s computer, including opening files, working in the browser, and running developer tools.
According to Engadget, the new feature allows Claude to first access connected services like Google Workspace or Slack, and if the required connector is not available, proceed to actions on the device itself. This means that the bot can not only search for information in integrated applications, but also actually interact with the local environment to bring the task to a result.
The company notes that Claude must ask for permission before doing so. At the same time, Anthropic advises against trusting this feature with sensitive data, as it is only a research preview, that is, an early research launch that will be further refined based on feedback. In the first phase, users of the paid Claude Pro and Claude Max plans on macOS will have access to computer control.
Separately, Anthropic is adding compatibility with Dispatch, which allows you to continue the same interaction with Claude across devices, including your phone and desktop, without breaking context. As a result, the company is pushing Claude beyond just a chatbot and into an assistant that can perform longer, more practical work scenarios, including actions in the file system, browser, and work tools.
For Anthropic, this is a logical step in the development of agent functions. Back in 2024, the company introduced computer use as a tool for the API, allowing the model to interact with the computer interface through mouse control, keyboard control and screen reading. Now this approach is gradually reaching Claude’s consumer products, where the line between chatbot, assistant and performer of actions on the device is becoming less and less visible.
Previously, dev.ua wrote about how Kyiv IT expert Roman Rader, who works as a Software Engineer at Superhuman (formerly known as Grammarly), made a humorous plugin for the AI assistant Claude Code.
Як нейромережі бачать вільну та незалежну Україну? Тест dev.ua
Нейронні мережі для генерації зображень бачать світ по-своєму, їхню логіку зрозуміти часом зовсім неможливо. Але таки хочеться. На честь Дня Незалежності України редакція dev.ua вирішила провести невеликий експеримент.
Ми задали чотирьом різним нейронним мережам п’ять однакових запитів: «прапор України», «День Незалежності України», «український Крим», «перемога України» та «українці». Отриманими результатами ми ділимося з вами нижче.
У TikTok тепер можна генерувати фон за допомогою нейромережі. Ми протестували її та ділимося результатами
У TikTok з’явилася нова функція «Розумний фон». З її допомогою як фон для тіктоків можна підставляти згенеровані нейромережею зображення. Редакція dev.ua протестувала цю технологію і ділиться своїми враженнями.