Security researchers hacked OpenAI's internal systems in under 72 hours using Claude
The Decoder · rss · 2026-09-19
- Three security researchers used Anthropic's Claude models to break into OpenAI's internal systems via its community forum in under 72 hours.
- The team says Opus 5 bypassed a common security measure that its predecessor couldn't defeat.
- The attack demonstrates how newer AI models dramatically cut the time and expertise needed to exploit security flaws, raising concerns about AI-driven offensive security.
More from Models
- Occamy 1.0, a Qwen3.5 MoE agentic multimodal model, trends on Hugging Face — Accio-Lab · 2026-09-19
- Google open-sources Fuse, a multi-agent framework for verifiable social reasoning in LLMs — google · 2026-09-19
- Two weeks with Grok bots: great orchestration model, but the model itself isn't smart enough — letandrewcook · 2026-09-19
- Context7 benchmarks Jev: 10-170x faster, 3-20x cheaper, but fails site-level reasoning — gaganghotra_ · 2026-09-19
- Jev vs GLM 5.3 at Chess: Checkmated in 29 Moves but 80x Cheaper Per Move — nutlope · 2026-09-19
- Jev Goes Open Source: Library Turns Any HF Model Into a Jev-Style API, Live on Featherless — Aizkmusic · 2026-09-19