Report: Hackers Used a Loosened-Guardrail Opus 5 to Breach OpenAI's Internal Monorepo
teortaxesTex · x · 2026-09-18
Per Andrew Curran, the recent hack was carried out using Opus 5—apparently a version with loosened cyber-guardrails—and the attackers successfully accessed OpenAI's internal monorepo. The unsettling question: if three individuals could pull this off, what could a nation-state do? Details remain unconfirmed, but the episode has fueled worries about relaxed model safety guardrails.
More from Models
- Fable 5.5 delayed as Anthropic reportedly bets OpenAI's Astra 6.2 won't beat it — haider1 · 2026-11-04
- Community asks Moonshot when Kimi K3.1 model weights will drop — bgmshana · 2026-11-04
- Meta's Muse Spark Open license counts distilled models as derivatives — aidenclarke_12 · 2026-11-04
- Tencent Hy4 trails GPT-6.1 on hard tests as Kimi K3.1 Pro beats it on two benchmarks — heyshrutimishra · 2026-11-04
- Tencent's Hy4 agent self-trained a smaller model that beat Tencent's own baseline — heyshrutimishra · 2026-11-04
- Hy4 tops open models in finance eval at 3.04, hallucination rate cut to 5.45% — heyshrutimishra · 2026-11-04