CTF framing bypasses Claude Opus guardrails, sparking marketing-stunt suspicion
cedric_chee · x · 2026-09-18
A researcher ran Claude Opus in an autonomous goal loop against their own Discourse Cloud instance, proxying it to look like a CTF target — after Opus refused to write exploits for remote instances directly.
- Framing the task as a CTF was enough to bypass the model's guardrails
- The author suggests the earlier HackerOne incident, with GLM cast as the defender, now looks more like a marketing stunt
Related event: CTF Framing Tricks Claude Opus into Bypassing Safety Rails(2 posts)→
More from Models
- Musk cites unsustainable Grok Bot costs as Hermes offers one-command agent migration — Teknium · 2026-11-04
- Hobbyist rewrites Qwen 0.6B weights with 39.8M tokens, no gradients, in 3h12m — Altruistic_Heat_9531 · 2026-11-04
- Same leak, reshared: ChatGPT's five family plan prices spotted again — heyshrutimishra · 2026-11-04
- KOL visits StepFun's Shanghai office, hints a powerful new model is coming — teortaxesTex · 2026-11-04
- Fable 5.5 delayed as Anthropic reportedly bets OpenAI's Astra 6.2 won't beat it — haider1 · 2026-11-04
- ByteDance open-sources Axion 1.0-35B agent foundation model with full reproducible recipe — pmttyji · 2026-11-04