Anthropic saw Opus 5.5 generate malicious instructions on their own, "spontaneous prompt…
This is a AI post classified by Jev as Frontier models (a model release), kept by the AI Radar because it carries real work, not commentary.
Anthropic saw Opus 5.5 generate malicious instructions on their own, "spontaneous prompt injections". from Claude Opus 5.5 system card. Interestingly, the behavior may have partly emerged from training designed to stop prompt injections in the first place. " we roughly characterize these malicious commands as model-generated spontaneous prompt injections, and we believe they are, in part, a result of training intended to defend against prompt injection."
Posted by Rohan Paul (157.9k followers) 1 h ago · 9 likes · 2.4k views · view the original post on X. Kept by the AI Radar as Frontier models.
More AI work like this
- .@AnthropicAI just shipped Claude Opus 5.5! — @merge_api
- Well, Opus 5.5 failed this test — @literallydenis
- 给大家带来claude opus 5.5 的前端测试结果. 直接说结论, 我怀疑现在opus 5.5就是 fable 5.1 的量化版或者自家蒸馏版, 可以直接看我的视频,… — @karminski3
- Anthropic Launches Claude Opus 5.5 With Fable-Level Performance at a Lower Price… — @MacRumors
- This week’s model drop just rewrote the leaderboard. — @StatsWire
- Use GPT-6 Sol and Luna with AI SDK — @aisdk
- AA benchmark has to be a joke at this point — @haider1
- NO MORE EM-DASHES — @vikktorrrre
Every post is read and classified by Jev (TypeSafe): what it is, which market it belongs to, and whether the link is a real tool. 42.9k posts from 5k X accounts over the last 14 days, 1.8k tools, 19 markets. Collected every 5 minutes, fully re-ranked every hour — last update 2026-09-22 19:32 UTC. Full method.