Current public baseline
As of this launch on July 6, 2026, this site uses Anthropic and Claude primary sources accessed during the build. Current docs list Claude Fable 5, Claude Opus 4.8, Claude Sonnet 5, and Claude Haiku 4.5 in the latest model comparison. The same docs list context windows, output limits, model IDs, and knowledge cutoffs.
The system prompts page lists dated prompt entries for Claude web and mobile surfaces and notes that those prompt updates do not apply to the API. That distinction matters when comparing a claude.ai answer to an API response.
Launch log
| Date | Public change tracked | Why it matters |
|---|---|---|
| 2026-07-06 | Site launch baseline compiled from Anthropic Usage Policy, model docs, system prompt docs, system cards, context docs, and Help Center hallucination guidance. | Establishes the first source-backed snapshot for refusal and limitation claims. |
| 2026-06 | Model docs list Claude Fable 5 and Claude Sonnet 5 with current specs and availability notes. | Model behavior and limits should be discussed by model ID and date, not by the generic word Claude. |
| 2026-05 | Claude Opus 4.8 docs describe behavior changes including adaptive thinking and unsupported sampling parameters. | API migrations can fail for reasons that look like model refusal but are parameter constraints. |
| 2026-03-16 | Claude Help Center article states that Claude can produce incorrect or misleading responses. | This is the primary-source anchor for hallucination warnings. |
| 2025-09-15 | Anthropic Usage Policy effective date for the launch baseline. | Policy text is the main source for refusal and enforcement boundaries. |
Weekly update template
Future updates should add one row per public documentation change: source URL, date accessed, affected page, changed claim, and whether the site content changed. If a public source disappears or moves, keep the old citation in the source index and add the replacement.
The freshness standard is simple: no claim about a current Claude boundary should survive a model or policy change without being rechecked.
FAQ
How often should this page be updated?
Weekly is the intended cadence, with immediate updates for major model, policy, or system prompt changes.
Why does freshness matter for Claude limitations?
Refusal handling, model specs, system prompts, and policy enforcement can change. Dated sources prevent stale claims from looking current.
Primary sources
- System Prompts Claude Platform Docs - Accessed July 6, 2026
Shows that Claude web and mobile system prompts are published and periodically updated, while API behavior differs.
- Models overview Claude Platform Docs - Accessed July 6, 2026
Provides current model IDs, context windows, output limits, knowledge cutoffs, and availability notes.
- What is new in Claude Sonnet 5 Claude Platform Docs - Accessed July 6, 2026
Documents behavior changes such as adaptive thinking, sampling-parameter restrictions, and tokenizer changes.
- What is new in Claude Opus 4.8 Claude Platform Docs - Accessed July 6, 2026
Documents Opus 4.8 behavior changes, refusal stop details, adaptive thinking, and unsupported sampling parameters.
- Model system cards Anthropic - Accessed July 6, 2026
Lists public Claude system cards and frames them as documents about capabilities, safety evaluations, and deployment decisions.
- Usage Policy Anthropic - Effective September 15, 2025
Defines prohibited uses, high-risk use requirements, enforcement language, and the policy basis for many safety refusals.