platform-guideline 1 linked patterns checked
Anthropic commitments on model deprecation and preservation
Discusses model deprecation and replacement impacts, the need for responsible deprecation processes, and the user and researcher costs of retiring models that people depend on.
Read with a purpose
What this source can teach
Use this source to understand a platform convention and the setting it was designed for.
- Start with the original. Open the source and find the guidance or example relevant to your task.
- Trace the connection. Use the claim notes below to see how this site applies the source to specific patterns.
- Check the setting. Compare the source's platform, people, and constraints with your own decision.
Pattern Decisions This Source Supports
| Pattern | Supported decision | Required contract | Claim note |
|---|---|---|---|
| Model update notice | Choose model update notice when users need to understand and act on AI model lifecycle, version, capability, deprecation, retirement, replacement, migration, or auto-upgrade changes. | The notice identifies the current model and replacement or new model in user-visible text. | Supports responsible handling of model replacement impacts on dependent users and workflows. |
Comparisons supported by this source
- Model update notice vs notification banner vs warning text vs phase beta banner vs confidence uncertainty display vs source grounding display
Supports accounting for model replacement impacts on dependent users.
Evidence Role
This source is treated as platform-guideline evidence. Its value comes from the specific claims and setting described above.
Publisher: Anthropic. Last checked: .