UNIT.City — місце, де люди працюють... КРАЩЕ! Обирай свій простір просто зараз 👉
Наталя ХандусенкоAI Eng
15 August 2025, 10:24
2025-08-15
Anthropic makes Claude's learning mode available to all users: the chatbot explains its coding decisions
Since April, the learning mode has been available only to Claude for Education users. When enabled, the chatbot attempts to guide the user to their own solution after asking a question, rather than providing a direct answer. Now, the tool is available to everyone.
Since April, the learning mode has been available only to Claude for Education users. When enabled, the chatbot attempts to guide the user to their own solution after asking a question, rather than providing a direct answer. Now, the tool is available to everyone.
Starting yesterday, Claude.ai users can find a new option called "Training" in the style drop-down menu. By enabling this mode, the chatbot will try to guide the user to a solution to the question. If desired, this feature can be turned off, writes Engadget.
Moreover, Anthropic offers two different versions of this feature via Claude Code:
"Explanation" mode, where Claude will generate summaries of his decision-making process as he works, giving the user a better understanding of what he is doing;
For IT beginners, there is a more reliable option, which is again called "Training".
In the second option, Claude will occasionally pause his work and mark the section with a "#TODO" comment to prompt the user to write five to ten lines of their code.
To try out these two features, you need to update Claude Code to the latest version and type “/output-styles.” You can then choose between the two modes or Claude’s default behavior.
“Learning mode is designed to help you not only get things done, but also grow and learn along the way, and better understand your codebase,” said Drew Benta, head of education at Anthropic. He hopes the new tools will enable any coder to become “a really good engineering manager.” In practice, this means that such users may not write most of the code, but they will develop a sense of how things work and where the code needs to be tweaked.
Looking ahead, Bent says Anthropic “doesn’t have all the answers, but we’re certainly trying to think of other features we can build” based on the learning mode. To do this, the company is giving developers access to new Claude Code styles so they can create their own learning modes. Users can also customize Claude’s communication style by creating their own custom queries for the chatbot.
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.