Anthropic пересмотрела ограничения на создание игр в Claude Code. Менее чем через неделю после появления в Claude Code правила, запрещающего воссоздавать существующие игры, Anthropic незаметно переписала его. Серверный флаг остался прежним: tengu_heron_brook. В правило внесли два изменения: - Теперь прямо разрешено создавать игры с механиками, похожими на механики существующих проектов. - Уточнено, что под воссозданием существующей игры подразумевается копирование её названия, персонажей, графики, музыки, уровней или внешнего вида. Кроме того, Anthropic добавила второй флаг, original_games_guidance, а в Claude Code 2.1.317 новая формулировка уже встроена непосредственно в приложение. Возможности отключить это ограничение по-прежнему нет.
Anthropic revises restrictions on game creation in Claude Code.
Anthropic revises restrictions on game creation in Claude Code. Less than a week after a rule appeared in Claude Code prohibiting the recreation of existing games, Anthropic quietly rewrote it. The server flag remained the same: tengu_heron_brook. The rule was amended…
AI Summary & Key Takeaways
- Anthropic revises restrictions on game creation in Claude Code
- Less than a week after a rule appeared in Claude Code prohibiting the recreation of existing games, Anthropic quietly rewrote it
- The server flag remained the same: tengu_heron_brook
Anthropic revises restrictions on game creation in Claude Code.
Related stories
How To Build The Future: Paul Graham & Amjad Masad
I think with AI, everyone will have to go through this period of denial and then depression and then eventually acceptance. Replet's like this iceberg where there's this visible bit above the water that's like look you just tell it in English what to do and it writes your code…
Useful: on GitHub we have collected a whole library of materials on reverse engineering - Awesome-REA with more than 1000 materials...
Useful: GitHub has compiled a whole library of materials on reverse engineering - Awesome-REA with more than 1000 materials for studying and analyzing programs. https://github.com/reacher-z/Awesome-REA Inside there are 1196 selected resources, 424 practical cases and 207 scientific papers. All…
Anthropic pushes ahead with pre-Thanksgiving IPO despite tech selloff, accepts lower valuation
Despite the tech selloff, Anthropic is pressing ahead with its IPO at a valuation of $1.25 to $1.75 trillion, well below the hoped-for $2 trillion. The Claude developer aims to raise $80 to $100 billion before Thanksgiving. Rival OpenAI has also recently had to cut its…
The most important report in AI right now
Recursive self-improvements has already begun. And this comes with proof from a third-party evaluator that had near unfettered access to internal anthropic systems, researchers, and basically everything else. So this all really started a few months ago when leaders of the top AI…

