Sonnet needs detailed coding prompts; Opus handles bigger context better
For coding work, can be capable, but it needs very clear and detailed instructions. When building a function, class, feature, or specific behavior, it needs enough context to know exactly what to make.
It is not trusted for in a program or system. Its work needs to be watched closely while it codes.
Opus 4.6 to 4.8 appears to understand more of the surrounding project and can work with less guidance. It is described as better at handling large projects and seeing how one decision can affect other parts of the system later.
Key points
- needs detailed instructions for coding tasks.
- It may work for , classes, , and specific behavior when enough context is given.
- It is not considered reliable for in a larger system.
- Opus 4.6 to 4.8 is described as better at understanding large projects with less guidance.
- Opus is seen as stronger at predicting how one decision can affect other parts of the code.