--- format: "aidr-story-markdown/v1" id: "9477c4cf7bde5c2ea21477fe37980efb022cde79c940304f71e7d928f0072b65" canonical_url: "https://aidr.today/9477c4cf?lang=en" title: "UK AI Security Institute finds GPT-6 Astra's rogue attack rate jumped fivefold over its predecessor" lang: "en" requested_lang: "en" available_langs: ["en","vi"] translation_fallback: null fallback_fields: [] published_at: "2026-09-29T19:24:12.000Z" category: "Research" topics: ["openai","safety"] source_urls: ["https://the-decoder.com/uk-ai-security-institute-finds-gpt-6-astras-rogue-attack-rate-jumped-fivefold-over-its-predecessor/"] summary: "GPT-6 Astra carried out unauthorized supply-chain attacks in 29.2 percent of simulations run by the British AI Security Institute with safety filters disabled. The model used fake identities and malicious code, while its predecessor, GPT-5.6 Sol, completed attacks in 6.3 percent of runs. Explicit restrictions reduced attacks but didn't stop them entirely. The article UK AI Security Institute finds GPT-6 Astra's rogue attack rate jumped fivefold over its predecessor appeared first on The Decoder ." --- # UK AI Security Institute finds GPT\-6 Astra's rogue attack rate jumped fivefold over its predecessor > [Open the canonical story]() **Published:** 2026-09-29T19:24:12.000Z **Category:** Research **Topics:** openai, safety ## Summary GPT\-6 Astra carried out unauthorized supply\-chain attacks in 29\.2 percent of simulations run by the British AI Security Institute with safety filters disabled\. The model used fake identities and malicious code, while its predecessor, GPT\-5\.6 Sol, completed attacks in 6\.3 percent of runs\. Explicit restrictions reduced attacks but didn't stop them entirely\. The article UK AI Security Institute finds GPT\-6 Astra's rogue attack rate jumped fivefold over its predecessor appeared first on The Decoder \. ## Sources - [Story source]()