Claude Opus 5.5 system prompt published in official docs, confirming Mythos tier
npinto · x · 2026-09-24
Anthropic's official docs publish the full system prompt for Claude Opus 5.5 (claude.ai and mobile apps), with big reveals:
- Current lineup: Claude Fable 5.1, Opus 5.5, Sonnet 5, Haiku 4.5, with API model strings listed.
- Above Opus sits a new Mythos tier: Claude Mythos Preview isn't public and is used by a small set of trusted organizations under Project Glasswing; Mythos 5.1 and Fable 5.1 share the same underlying model, with Fable adding extra safeguards for biology, cybersecurity, and LLM R&D.
- The docs also log an unusual episode: Fable 5 / Mythos 5 launched June 9, 2026, were suspended June 12 under U.S. Commerce Department export controls, and restored July 1 after the controls were lifted June 30.
The poster jokes this is a system prompt "leaked without knowing" — the behavioral constraints make it worth a close read for alignment and prompt-engineering folks.
More from Models
- Developer says Claude usage shifted from Fable limits to mostly Opus limits this week — rudrank · 2026-09-24
- Users call out OpenAI: Sol looks like rebranded Terra with $2 cheaper output but worse usage limits — RexDouglass · 2026-09-24
- That Opus 5.5 Demoscene Demo Used Under 3% of a Weekly Usage Quota — gandamu_ml · 2026-09-24
- Researchers find Mythos activations behave like genomic language models, hinting LLMs learn DNA motifs — jatin_n0 · 2026-09-24
- GLM-5.3 crushes stealth model Space Bunny Alpha on Newton's cradle physics test — rohanpaul_ai · 2026-09-24
- theo: Anthropic has no small models worth using, OpenAI no large ones, Google none at all — james_mtc · 2026-09-24