Anthropic targets coders working on AI agents with latest release
Pro
Image: Dennis
Anthropic is releasing a new version of its Sonnet model – 4.5 – which its creators claim is the best in software writing for apps and complex AI agents.
This claim is not made for shock value, as Claude models are indeed highly regarded in the world of programmers and software developers.
Claude Code, as the version for engineers is called, has introduced a few key improvements. Among them checkpoints that allow users to save their progress and immediately return to an earlier stage, and a revamped terminal interface and a native VS Code extension.
The Claude API has been enhanced with a new context editing feature and memory tool that enables agents to perform more complex and longer tasks, while in the Claude apps, code can now be executed directly and files such as spreadsheets, presentations and documents can be created.
These are all steps towards an environment where a human will barely be needed to write software.
Emerce