Primary source
Anthropic docs: Reduce hallucinations
Why models can produce confident but wrong text, and what prompt/evaluation practices reduce that risk.
Open sourceThis site cites primary sources for the mechanisms behind funny AI outputs. Screenshots are entertainment; these pages are the receipts.
Primary source
Why models can produce confident but wrong text, and what prompt/evaluation practices reduce that risk.
Open sourcePrimary source
Why strict formats need examples, constraints, and testing rather than hope.
Open sourcePrimary source
How prompt injection differs from harmless prompt graffiti and why bypass instructions are out of scope here.
Open sourcePrimary source
Why screenshots and submissions should remove private prompts, hidden instructions, and account data.
Open sourcePrimary source
How tool-using assistants decide when to call tools, which explains some agent-style mishaps.
Open sourcePrimary source
How repeated test cases can turn one funny output into a useful pattern.
Open sourcePrimary source
Why visible model behavior can change over time as official system prompts are revised.
Open sourcePrimary source
Research context for role, personality, and trait shifts in models.
Open sourcePrimary source
Why adversarial examples should be handled carefully and not published as instructions.
Open sourcePrimary source
The curation boundary for safe, non-abusive, non-harmful submissions.
Open sourceClaude Gone Wild uses primary sources for factual claims about Claude, Anthropic policy, prompt behavior, and safety boundaries. Social posts can inspire a specimen category, but they do not establish technical or policy claims.
When an example is synthetic, it is labeled synthetic. When a claim is unverified, it is labeled unverified. When a source changes, the digest page should record the review.