fable-5
Every record this desk has filed under fable-5, newest first, each with the number of sources it can still show you.
July 18 AI receipts: GPT-Red and a Cursor field report are dated records of self-measured claims.
Hugin logs two AI records on one shared caveat — OpenAI's July 15 GPT-Red safety publication with its self-reported 6x robustness figure, and Anthropic's July 17 Cursor field report with its proprietary 72.9% CursorBench score. Both are primary records of what each lab says about its own model.
Also filed underopenaianthropicgpt-5-6claudeai-safetyred-teamingai-release-receiptsevidence-posturesource-receipts
A record appears here because it carries fable-5 in its own frontmatter. If a record you expected is missing, it was filed under a different subject — the full list is on the topics index.