Tag
Anthropic outlines a six-step process for conducting large-scale code migrations using Claude Code, focusing on creating rulebooks, dependency maps, and iterative validation with a strong judge.
Bun official blog announces rewriting Bun in Rust, and with the help of 64 Claude AI instances automatically detects, modifies, reviews and fixes code errors in Rust projects in batches, reflecting the unexpectedly good effect of AI in code porting.
Copybara is an open-source tool from Google that transforms and moves code between repositories, commonly used to sync confidential and public repositories with a single source of truth.
IBM Research introduces ScarfBench, an open benchmark for evaluating AI agents on cross-framework Java migration tasks, focusing on Spring, Jakarta EE, and Quarkus. The benchmark assesses whether migrated applications build, deploy, and preserve behavior, unlike traditional code generation benchmarks.
An in-depth article on mastering OpenAI Codex, covering a complete knowledge system from mental models to practical applications such as large-scale code migration, security auditing, performance optimization, team collaboration, building a personal AI operating system, and product development.
Anthropic released Claude Fable 5 on June 9, a “Mythos”-class model that leads benchmarks in coding, research, and visual processing, especially good at large-scale projects like code migration. It is now available to Pro, Max, Team, and Enterprise users.
Anthropic released Fable 5, a mythos-class public model, which in a demo migrated a 50 million line Ruby codebase in one day—a job estimated to take engineers over two months, sparking discussions about the future of engineering jobs.