Anthropic says these topics are too dangerous to let its Fable 5 model talk about
Anthropic's new frontier model Fable 5 refuses to answer queries on cybersecurity, biology, and chemistry.
Anthropic has announced that its latest frontier model, Fable 5, enforces hard refusals on topics deemed too dangerous, specifically cybersecurity, biology, and chemistry. The move reflects the company's ongoing effort to balance capability with safety as models grow more powerful. For developers and researchers in these fields, the restrictions may limit practical usability in legitimate professional contexts.
Anthropic 在 2026 年 6 月正式公開說明，其最新一代前沿語言模型 Fable 5 針對特定主題類別設有強制性拒絕機制，被列為「過於危險」而不允許模型回應的領域包括：網路安全（cybersecurity）、生物學（biology）以及化學（chemistry）。
Free shows the 3-line summary; Pro unlocks the full deep summary (~300 words) so you never have to click through.
See Pro plans →Want the original English / full article?
Read on Ars Technica AI →Summaries are AI-generated; the original article is authoritative.